diff --git "a/awesome-japanese-nlp-resources-search.json" "b/awesome-japanese-nlp-resources-search.json" --- "a/awesome-japanese-nlp-resources-search.json" +++ "b/awesome-japanese-nlp-resources-search.json" @@ -3,9 +3,9 @@ "description": "Fine-tuned XLSR-53 large model for speech recognition in Japanese Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using the train and validation splits of Common Voice 6.1, CSS10 and JSUT.", "url": "https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-japanese", "project_name": "wav2vec2-large-xlsr-53-japanese", - "downloads": 1030012, + "downloads": 2251749, "source": "Hugging Face", - "score": 16.068440033848738, + "score": 23.786891762662968, "first_commit": "2021-04-16 00:20:03", "latest_commit": "2022-12-14 01:58:09", "languages": [], @@ -19,7 +19,7 @@ "project_name": "donut", "stargazers_count": 5553, "source": "GitHub", - "score": 15.941514700048343, + "score": 15.989817280615636, "first_commit": "2022-07-20 23:15:30", "latest_commit": "2023-07-31 15:14:20", "languages": [ @@ -31,9 +31,9 @@ "description": "xlm-roberta-ner-japanese (Japanese caption : 日本語の固有表現抽出のモデル)", "url": "https://huggingface.co/tsmatz/xlm-roberta-ner-japanese", "project_name": "xlm-roberta-ner-japanese", - "downloads": 985676, + "downloads": 1002653, "source": "Hugging Face", - "score": 15.371861323453928, + "score": 10.540290467530491, "first_commit": "2022-10-24 02:08:37", "latest_commit": "2024-07-12 00:01:56", "languages": [], @@ -45,9 +45,9 @@ "description": "BERT base Japanese (IPA dictionary)", "url": "https://huggingface.co/tohoku-nlp/bert-base-japanese", "project_name": "bert-base-japanese", - "downloads": 918614, + "downloads": 929186, "source": "Hugging Face", - "score": 14.31822632082634, + "score": 9.761176566477651, "first_commit": "2020-04-28 21:34:23", "latest_commit": "2024-02-22 00:57:00", "languages": [], @@ -61,7 +61,7 @@ "project_name": "mecab-ipadic-neologd", "stargazers_count": 2695, "source": "GitHub", - "score": 7.563167628043869, + "score": 7.587238516506822, "first_commit": "2015-03-09 16:46:28", "latest_commit": "2020-09-14 19:56:40", "languages": [ @@ -75,7 +75,7 @@ "project_name": "voicevox", "stargazers_count": 2411, "source": "GitHub", - "score": 6.7306096964660975, + "score": 6.752272677106226, "first_commit": "2021-08-01 02:41:10", "latest_commit": "2024-08-16 01:45:33", "languages": [ @@ -90,7 +90,7 @@ "project_name": "mozc", "stargazers_count": 2333, "source": "GitHub", - "score": 6.50194941948347, + "score": 6.52295107332719, "first_commit": "2010-05-10 12:05:41", "latest_commit": "2024-08-15 07:37:57", "languages": [ @@ -98,27 +98,13 @@ ], "model_or_dataset": null }, - { - "description": "BERT base Japanese (IPA dictionary, whole word masking enabled)", - "url": "https://huggingface.co/tohoku-nlp/bert-base-japanese-whole-word-masking", - "project_name": "bert-base-japanese-whole-word-masking", - "downloads": 365036, - "source": "Hugging Face", - "score": 5.620764904755031, - "first_commit": "2020-04-28 21:34:35", - "latest_commit": "2024-02-22 00:57:37", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForMaskedLM" - }, { "description": "Engineer Vocabulary List in Japanese/English", "url": "https://github.com/mercari/engineer-vocabulary-list", "project_name": "engineer-vocabulary-list", "stargazers_count": 1766, "source": "GitHub", - "score": 4.839765098340524, + "score": 4.855959415087267, "first_commit": "2020-09-30 14:16:14", "latest_commit": "2020-11-04 08:32:10", "languages": [], @@ -130,7 +116,7 @@ "project_name": "manga-ocr", "stargazers_count": 1517, "source": "GitHub", - "score": 4.109811137203676, + "score": 4.1238942953311115, "first_commit": "2022-01-15 18:18:35", "latest_commit": "2024-06-29 11:23:04", "languages": [ @@ -144,7 +130,7 @@ "project_name": "N46Whisper", "stargazers_count": 1515, "source": "GitHub", - "score": 4.103948053178479, + "score": 4.118014254208572, "first_commit": "2022-10-25 16:27:20", "latest_commit": "2024-06-30 15:22:02", "languages": [ @@ -153,27 +139,13 @@ ], "model_or_dataset": null }, - { - "description": "GLuCoSE (General Luke-based Contrastive Sentence Embedding)-base-Japanese 日本語のREADME/Japanese README GLuCoSE (General LUke-based COntrastive Sentence Embedding, \"glucose\") is a Japanese text embedding model based on LUKE.", - "url": "https://huggingface.co/pkshatech/GLuCoSE-base-ja", - "project_name": "GLuCoSE-base-ja", - "downloads": 261805, - "source": "Hugging Face", - "score": 3.9988658418543066, - "first_commit": "2023-07-16 07:28:46", - "latest_commit": "2023-08-25 02:53:22", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LukeModel" - }, { "description": "Manga OCR Optical character recognition for Japanese text, with the main focus being Japanese manga.", "url": "https://huggingface.co/kha-white/manga-ocr-base", "project_name": "manga-ocr-base", - "downloads": 256277, + "downloads": 372642, "source": "Hugging Face", - "score": 3.9120134620486744, + "score": 3.859054975184262, "first_commit": "2022-01-15 17:39:06", "latest_commit": "2022-06-22 15:34:05", "languages": [], @@ -187,7 +159,7 @@ "project_name": "voicevox_engine", "stargazers_count": 1257, "source": "GitHub", - "score": 3.3476102139282506, + "score": 3.3594889494009883, "first_commit": "2021-08-02 02:39:41", "latest_commit": "2024-08-15 01:08:26", "languages": [ @@ -201,7 +173,7 @@ "project_name": "ojichat", "stargazers_count": 1249, "source": "GitHub", - "score": 3.3241578778274685, + "score": 3.335968784910831, "first_commit": "2019-05-25 03:44:08", "latest_commit": "2023-04-23 16:02:15", "languages": [ @@ -215,7 +187,7 @@ "project_name": "yomichan", "stargazers_count": 1044, "source": "GitHub", - "score": 2.723191765244922, + "score": 2.7332645698505416, "first_commit": "2016-03-16 20:33:15", "latest_commit": "2023-02-25 12:43:18", "languages": [ @@ -224,13 +196,27 @@ ], "model_or_dataset": null }, + { + "description": "BERT base Japanese (IPA dictionary, whole word masking enabled)", + "url": "https://huggingface.co/tohoku-nlp/bert-base-japanese-whole-word-masking", + "project_name": "bert-base-japanese-whole-word-masking", + "downloads": 261740, + "source": "Hugging Face", + "score": 2.682944750803765, + "first_commit": "2020-04-28 21:34:35", + "latest_commit": "2024-02-22 00:57:37", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "BertForMaskedLM" + }, { "description": "Kuromoji is a self-contained and very easy to use Japanese morphological analyzer designed for search", "url": "https://github.com/atilika/kuromoji", "project_name": "kuromoji", "stargazers_count": 941, "source": "GitHub", - "score": 2.42124293794735, + "score": 2.4304424520397623, "first_commit": "2011-01-20 15:26:44", "latest_commit": "2019-09-23 11:13:04", "languages": [ @@ -244,7 +230,7 @@ "project_name": "mecab", "stargazers_count": 908, "source": "GitHub", - "score": 2.324502051531623, + "score": 2.333421773517862, "first_commit": "2011-10-15 15:16:30", "latest_commit": "2023-05-24 16:04:25", "languages": [ @@ -258,13 +244,27 @@ ], "model_or_dataset": null }, + { + "description": "GLuCoSE (General Luke-based Contrastive Sentence Embedding)-base-Japanese 日本語のREADME/Japanese README GLuCoSE (General LUke-based COntrastive Sentence Embedding, \"glucose\") is a Japanese text embedding model based on LUKE.", + "url": "https://huggingface.co/pkshatech/GLuCoSE-base-ja", + "project_name": "GLuCoSE-base-ja", + "downloads": 227805, + "source": "Hugging Face", + "score": 2.3230657543532756, + "first_commit": "2023-07-16 07:28:46", + "latest_commit": "2023-08-25 02:53:22", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "LukeModel" + }, { "description": "オープンソースの日本語LLMまとめ", "url": "https://github.com/llm-jp/awesome-japanese-llm", "project_name": "awesome-japanese-llm", "stargazers_count": 879, "source": "GitHub", - "score": 2.239487333166287, + "score": 2.2481611772410406, "first_commit": "2023-07-09 13:36:38", "latest_commit": "2024-08-10 19:11:35", "languages": [ @@ -278,7 +278,7 @@ "project_name": "janome", "stargazers_count": 843, "source": "GitHub", - "score": 2.133951820712767, + "score": 2.1423204370353313, "first_commit": "2015-02-14 18:45:54", "latest_commit": "2023-07-01 20:31:23", "languages": [ @@ -292,7 +292,7 @@ "project_name": "voicevox_core", "stargazers_count": 839, "source": "GitHub", - "score": 2.1222256526623755, + "score": 2.1305603547902523, "first_commit": "2021-08-31 23:19:33", "latest_commit": "2024-08-14 00:00:48", "languages": [ @@ -310,7 +310,7 @@ "project_name": "kuromoji.js", "stargazers_count": 831, "source": "GitHub", - "score": 2.0987733165615934, + "score": 2.107040190300095, "first_commit": "2014-12-04 17:31:39", "latest_commit": "2018-11-24 16:05:09", "languages": [ @@ -324,7 +324,7 @@ "project_name": "budoux", "stargazers_count": 815, "source": "GitHub", - "score": 2.0518686443600287, + "score": 2.0599998613197794, "first_commit": "2021-11-18 09:36:21", "latest_commit": "2024-08-16 15:09:25", "languages": [ @@ -341,7 +341,7 @@ "project_name": "kagome", "stargazers_count": 803, "source": "GitHub", - "score": 2.0166901402088553, + "score": 2.024719614584543, "first_commit": "2014-06-26 13:52:06", "latest_commit": "2024-08-13 10:35:54", "languages": [ @@ -356,7 +356,7 @@ "project_name": "kuroshiro", "stargazers_count": 787, "source": "GitHub", - "score": 1.9697854680072908, + "score": 1.977679285604228, "first_commit": "2016-01-03 17:16:40", "latest_commit": "2021-06-07 23:02:39", "languages": [ @@ -370,7 +370,7 @@ "project_name": "mokuro", "stargazers_count": 781, "source": "GitHub", - "score": 1.9521962159317041, + "score": 1.9600391622366098, "first_commit": "2022-04-16 14:44:52", "latest_commit": "2024-07-09 17:10:55", "languages": [ @@ -380,27 +380,13 @@ ], "model_or_dataset": null }, - { - "description": "This is a Japanese sentence-BERT model. ", - "url": "https://huggingface.co/sonoisa/sentence-bert-base-ja-mean-tokens-v2", - "project_name": "sentence-bert-base-ja-mean-tokens-v2", - "downloads": 129262, - "source": "Hugging Face", - "score": 1.9164354915326902, - "first_commit": "2021-12-14 11:18:19", - "latest_commit": "2024-04-17 11:39:38", - "languages": [], - "model_or_dataset": "model", - "model_size": 0.111, - "model_architectures": "BertModel" - }, { "description": "Javascript library for detecting and transliterating Hiragana <--> Katakana <--> Romaji", "url": "https://github.com/WaniKani/WanaKana", "project_name": "WanaKana", "stargazers_count": 738, "source": "GitHub", - "score": 1.8261399093899993, + "score": 1.8336182781020125, "first_commit": "2013-08-27 12:57:41", "latest_commit": "2023-11-20 12:22:09", "languages": [ @@ -409,13 +395,27 @@ ], "model_or_dataset": null }, + { + "description": "This is a Japanese sentence-BERT model.", + "url": "https://huggingface.co/sonoisa/sentence-bert-base-ja-mean-tokens-v2", + "project_name": "sentence-bert-base-ja-mean-tokens-v2", + "downloads": 180115, + "source": "Hugging Face", + "score": 1.817315663275514, + "first_commit": "2021-12-14 11:18:19", + "latest_commit": "2024-04-17 11:39:38", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.111, + "model_architectures": "BertModel" + }, { "description": "A Japanese NLP Library using spaCy as framework based on Universal Dependencies", "url": "https://github.com/megagonlabs/ginza", "project_name": "ginza", "stargazers_count": 731, "source": "GitHub", - "score": 1.8056191153018146, + "score": 1.8130381341731245, "first_commit": "2019-03-11 16:49:15", "latest_commit": "2024-03-31 07:29:06", "languages": [ @@ -429,7 +429,7 @@ "project_name": "shuwa", "stargazers_count": 726, "source": "GitHub", - "score": 1.7909614052388259, + "score": 1.798338031366776, "first_commit": "2021-04-20 14:25:55", "latest_commit": "2022-12-22 19:41:35", "languages": [ @@ -444,7 +444,7 @@ "project_name": "luke", "stargazers_count": 699, "source": "GitHub", - "score": 1.7118097708986855, + "score": 1.718957476212494, "first_commit": "2020-03-31 21:56:47", "latest_commit": "2023-06-16 23:11:54", "languages": [ @@ -459,7 +459,7 @@ "project_name": "japanese-addresses", "stargazers_count": 698, "source": "GitHub", - "score": 1.7088782288860878, + "score": 1.7160174556512242, "first_commit": "2020-07-12 13:35:51", "latest_commit": "2024-01-15 09:28:19", "languages": [ @@ -468,18 +468,18 @@ "model_or_dataset": "dataset" }, { - "description": "BERT base Japanese (character tokenization)", - "url": "https://huggingface.co/tohoku-nlp/bert-base-japanese-char", - "project_name": "bert-base-japanese-char", - "downloads": 113979, + "description": "rinna/japanese-cloob-vit-b-16", + "url": "https://huggingface.co/rinna/japanese-cloob-vit-b-16", + "project_name": "japanese-cloob-vit-b-16", + "downloads": 170181, "source": "Hugging Face", - "score": 1.6763188271749703, - "first_commit": "2020-04-28 21:34:05", - "latest_commit": "2024-02-22 00:57:58", + "score": 1.7119660846475737, + "first_commit": "2022-04-27 08:29:29", + "latest_commit": "2024-07-22 08:09:24", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForMaskedLM" + "model_size": 0.197, + "model_architectures": "CLOOBModel" }, { "description": "ChatdollKit enables you to make your 3D model into a chatbot", @@ -487,7 +487,7 @@ "project_name": "ChatdollKit", "stargazers_count": 685, "source": "GitHub", - "score": 1.6707681827223164, + "score": 1.6777971883547182, "first_commit": "2020-03-21 22:01:11", "latest_commit": "2024-07-21 01:41:49", "languages": [ @@ -501,7 +501,7 @@ "project_name": "normalize-japanese-addresses", "stargazers_count": 672, "source": "GitHub", - "score": 1.6326581365585453, + "score": 1.639576921058212, "first_commit": "2020-05-30 10:53:34", "latest_commit": "2024-07-02 10:44:21", "languages": [ @@ -510,27 +510,13 @@ ], "model_or_dataset": null }, - { - "description": "BERT base Japanese (character-level tokenization with whole word masking, jawiki-20200831)", - "url": "https://huggingface.co/tohoku-nlp/bert-base-japanese-char-v2", - "project_name": "bert-base-japanese-char-v2", - "downloads": 108094, - "source": "Hugging Face", - "score": 1.5838574930295026, - "first_commit": "2021-03-05 04:05:08", - "latest_commit": "2021-09-23 15:45:24", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForMaskedLM" - }, { "description": "Automatically exported from code.google.com/p/mozc-morse", "url": "https://github.com/google/mozc-devices", "project_name": "mozc-devices", "stargazers_count": 635, "source": "GitHub", - "score": 1.5241910820924272, + "score": 1.530796160291233, "first_commit": "2012-06-06 06:06:16", "latest_commit": "2024-02-28 20:08:36", "languages": [ @@ -540,27 +526,13 @@ ], "model_or_dataset": null }, - { - "description": "rinna/japanese-cloob-vit-b-16", - "url": "https://huggingface.co/rinna/japanese-cloob-vit-b-16", - "project_name": "japanese-cloob-vit-b-16", - "downloads": 94886, - "source": "Hugging Face", - "score": 1.3763418938122833, - "first_commit": "2022-04-27 08:29:29", - "latest_commit": "2024-07-22 08:09:24", - "languages": [], - "model_or_dataset": "model", - "model_size": 0.197, - "model_architectures": "CLOOBModel" - }, { "description": "Code for producing Japanese pretrained models provided by rinna Co., Ltd.", "url": "https://github.com/rinnakk/japanese-pretrained-models", "project_name": "japanese-pretrained-models", "stargazers_count": 576, "source": "GitHub", - "score": 1.3512301033491578, + "score": 1.3573349471763205, "first_commit": "2021-04-06 13:48:14", "latest_commit": "2022-10-28 16:08:26", "languages": [ @@ -574,7 +546,7 @@ "project_name": "mecab-python3", "stargazers_count": 515, "source": "GitHub", - "score": 1.1724060405806926, + "score": 1.1779936929388686, "first_commit": "2014-05-31 17:47:48", "latest_commit": "2024-04-15 21:32:53", "languages": [ @@ -589,7 +561,7 @@ "project_name": "bert-japanese", "stargazers_count": 502, "source": "GitHub", - "score": 1.1342959944169215, + "score": 1.1397734256423624, "first_commit": "2019-03-24 22:50:33", "latest_commit": "2024-03-24 00:08:38", "languages": [ @@ -604,7 +576,7 @@ "project_name": "bert-japanese", "stargazers_count": 497, "source": "GitHub", - "score": 1.1196382843539325, + "score": 1.125073322836014, "first_commit": "2018-12-27 20:05:33", "latest_commit": "2021-02-15 10:20:28", "languages": [ @@ -614,17 +586,31 @@ "model_or_dataset": "model" }, { - "description": "This is a Japanese sentence-BERT model.", - "url": "https://huggingface.co/sonoisa/sentence-bert-base-ja-mean-tokens", - "project_name": "sentence-bert-base-ja-mean-tokens", - "downloads": 76653, + "description": "BERT base Japanese (character tokenization)", + "url": "https://huggingface.co/tohoku-nlp/bert-base-japanese-char", + "project_name": "bert-base-japanese-char", + "downloads": 113765, "source": "Hugging Face", - "score": 1.089876727206623, - "first_commit": "2021-07-22 06:11:37", - "latest_commit": "2024-04-17 11:40:03", + "score": 1.1136771951897628, + "first_commit": "2020-04-28 21:34:05", + "latest_commit": "2024-02-22 00:57:58", "languages": [], "model_or_dataset": "model", - "model_size": 0.111, + "model_size": null, + "model_architectures": "BertForMaskedLM" + }, + { + "description": "BERT base Japanese (character-level tokenization with whole word masking, jawiki-20200831)", + "url": "https://huggingface.co/tohoku-nlp/bert-base-japanese-char-v2", + "project_name": "bert-base-japanese-char-v2", + "downloads": 109410, + "source": "Hugging Face", + "score": 1.0674926356040288, + "first_commit": "2021-03-05 04:05:08", + "latest_commit": "2021-09-23 15:45:24", + "languages": [], + "model_or_dataset": "model", + "model_size": null, "model_architectures": "BertForMaskedLM" }, { @@ -633,7 +619,7 @@ "project_name": "rakutenma", "stargazers_count": 471, "source": "GitHub", - "score": 1.04341819202639, + "score": 1.0486327882430015, "first_commit": "2014-08-05 19:05:12", "latest_commit": "2015-01-29 18:28:18", "languages": [ @@ -647,7 +633,7 @@ "project_name": "bangumi-data", "stargazers_count": 471, "source": "GitHub", - "score": 1.04341819202639, + "score": 1.0486327882430015, "first_commit": "2016-09-05 10:17:46", "latest_commit": "2024-08-12 10:50:17", "languages": [ @@ -656,41 +642,13 @@ ], "model_or_dataset": null }, - { - "description": "This is a Japanese sentence-LUKE model.", - "url": "https://huggingface.co/sonoisa/sentence-luke-japanese-base-lite", - "project_name": "sentence-luke-japanese-base-lite", - "downloads": 69418, - "source": "Hugging Face", - "score": 0.9762050615239624, - "first_commit": "2023-03-19 14:44:42", - "latest_commit": "2023-03-20 01:32:34", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LukeModel" - }, - { - "description": "BERT base Japanese (unidic-lite with whole word masking, CC-100 and jawiki-20230102)", - "url": "https://huggingface.co/tohoku-nlp/bert-base-japanese-v3", - "project_name": "bert-base-japanese-v3", - "downloads": 68993, - "source": "Hugging Face", - "score": 0.9695277349289202, - "first_commit": "2023-05-19 00:13:53", - "latest_commit": "2023-05-19 00:31:53", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForPreTraining" - }, { "description": "JMMLU Japanese Massive Multitask Language Understanding Benchmark JMMLU is a four-choice question set consisting of Japanese-translated questions of a portion of MMLU (Paper, Github) (Translated questions) and questions based on unique Japanese cultural context (Japanese questions).", "url": "https://huggingface.co/datasets/nlp-waseda/JMMLU", "project_name": "JMMLU", - "downloads": 67721, + "downloads": 90961, "source": "Hugging Face", - "score": 0.949542889213876, + "score": 0.8718419031592056, "first_commit": "2024-02-09 12:19:13", "latest_commit": "2024-02-27 05:22:30", "languages": [], @@ -698,27 +656,13 @@ "model_size": null, "model_architectures": null }, - { - "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", - "url": "https://huggingface.co/tokyotech-llm/Swallow-7b-instruct-hf", - "project_name": "Swallow-7b-instruct-hf", - "downloads": 62180, - "source": "Hugging Face", - "score": 0.8624862617712191, - "first_commit": "2023-12-07 02:18:36", - "latest_commit": "2024-06-29 08:56:26", - "languages": [], - "model_or_dataset": "model", - "model_size": 6.83, - "model_architectures": "LlamaForCausalLM" - }, { "description": "Lightweight converter from Japanese Kana-kanji sentences into Kana-Roman.", "url": "https://github.com/miurahr/pykakasi", "project_name": "pykakasi", "stargazers_count": 407, "source": "GitHub", - "score": 0.8557995032201318, + "score": 0.8604714723217406, "first_commit": "2011-01-26 09:56:25", "latest_commit": "2022-07-22 12:36:37", "languages": [ @@ -727,32 +671,18 @@ "model_or_dataset": null }, { - "description": "shisa-gamma-7b-v1 For more information see our main Shisa 7B model We applied a version of our fine-tune data set onto Japanese Stable LM Base Gamma 7B and it performed pretty well, just sharing since it might be of interest.", - "url": "https://huggingface.co/augmxnt/shisa-gamma-7b-v1", - "project_name": "shisa-gamma-7b-v1", - "downloads": 59480, - "source": "Hugging Face", - "score": 0.8200655986968329, - "first_commit": "2023-12-23 20:21:44", - "latest_commit": "2024-05-19 06:07:36", - "languages": [], - "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": "MistralForCausalLM" - }, - { - "description": "Sentence BERT base Japanese model This repository contains a Sentence BERT base model for Japanese.", - "url": "https://huggingface.co/colorfulscoop/sbert-base-ja", - "project_name": "sbert-base-ja", - "downloads": 57043, + "description": "This is a Japanese sentence-BERT model.", + "url": "https://huggingface.co/sonoisa/sentence-bert-base-ja-mean-tokens", + "project_name": "sentence-bert-base-ja-mean-tokens", + "downloads": 83440, "source": "Hugging Face", - "score": 0.7817770224330258, - "first_commit": "2021-08-01 04:12:28", - "latest_commit": "2021-08-08 15:47:42", + "score": 0.7920820701754386, + "first_commit": "2021-07-22 06:11:37", + "latest_commit": "2024-04-17 11:40:03", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertModel" + "model_size": 0.111, + "model_architectures": "BertForMaskedLM" }, { "description": "テキストを壱百満天原サロメお嬢様風の口調に変換します", @@ -760,7 +690,7 @@ "project_name": "ojosama", "stargazers_count": 380, "source": "GitHub", - "score": 0.7766478688799915, + "score": 0.7810909171674586, "first_commit": "2022-06-16 07:21:02", "latest_commit": "2024-08-07 00:15:14", "languages": [ @@ -774,7 +704,7 @@ "project_name": "fugashi", "stargazers_count": 376, "source": "GitHub", - "score": 0.7649217008296003, + "score": 0.7693308349223799, "first_commit": "2019-10-14 13:33:36", "latest_commit": "2024-04-15 21:15:01", "languages": [ @@ -788,7 +718,7 @@ "project_name": "nagisa", "stargazers_count": 376, "source": "GitHub", - "score": 0.7649217008296003, + "score": 0.7693308349223799, "first_commit": "2018-02-14 23:56:05", "latest_commit": "2024-06-15 01:55:19", "languages": [ @@ -802,7 +732,7 @@ "project_name": "jumanpp", "stargazers_count": 372, "source": "GitHub", - "score": 0.7531955327792091, + "score": 0.757570752677301, "first_commit": "2016-10-17 14:48:20", "latest_commit": "2023-03-06 09:27:42", "languages": [ @@ -819,7 +749,7 @@ "project_name": "lindera", "stargazers_count": 369, "source": "GitHub", - "score": 0.7444009067414158, + "score": 0.748750690993492, "first_commit": "2020-01-22 23:29:22", "latest_commit": "2024-07-15 23:23:30", "languages": [ @@ -833,7 +763,7 @@ "project_name": "ndlocr_cli", "stargazers_count": 344, "source": "GitHub", - "score": 0.6711123564264712, + "score": 0.6752501769617494, "first_commit": "2022-03-30 11:12:01", "latest_commit": "2024-07-29 09:20:46", "languages": [ @@ -847,7 +777,7 @@ "project_name": "camphr", "stargazers_count": 340, "source": "GitHub", - "score": 0.65938618837608, + "score": 0.6634900947166705, "first_commit": "2019-08-27 07:22:43", "latest_commit": "2021-08-18 15:06:51", "languages": [ @@ -861,7 +791,7 @@ "project_name": "aquaskk", "stargazers_count": 339, "source": "GitHub", - "score": 0.6564546463634822, + "score": 0.6605500741554009, "first_commit": "2013-05-12 07:03:33", "latest_commit": "2023-07-10 00:35:46", "languages": [ @@ -875,7 +805,7 @@ "project_name": "kanji-data-media", "stargazers_count": 336, "source": "GitHub", - "score": 0.6476600203256888, + "score": 0.6517300124715918, "first_commit": "2014-08-30 19:06:48", "latest_commit": "2023-11-15 20:28:16", "languages": [], @@ -887,7 +817,7 @@ "project_name": "emoji-ime-dictionary", "stargazers_count": 331, "source": "GitHub", - "score": 0.6330023102626999, + "score": 0.6370299096652432, "first_commit": "2018-10-13 21:37:28", "latest_commit": "2023-01-16 12:01:31", "languages": [ @@ -901,7 +831,7 @@ "project_name": "animedb", "stargazers_count": 321, "source": "GitHub", - "score": 0.603686890136722, + "score": 0.6076297040525462, "first_commit": "2016-10-11 23:05:11", "latest_commit": "2023-01-04 16:56:30", "languages": [ @@ -909,27 +839,13 @@ ], "model_or_dataset": "dataset" }, - { - "description": "JMTEB:", - "url": "https://huggingface.co/datasets/sbintuitions/JMTEB", - "project_name": "JMTEB", - "downloads": 44658, - "source": "Hugging Face", - "score": 0.5871918697751471, - "first_commit": "2024-02-22 18:15:27", - "latest_commit": "2024-06-28 15:18:20", - "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null - }, { "description": "Japanese GPT2 Generation Model", "url": "https://github.com/tanreinama/gpt2-japanese", "project_name": "gpt2-japanese", "stargazers_count": 313, "source": "GitHub", - "score": 0.5802345540359397, + "score": 0.5841095395623886, "first_commit": "2019-12-12 11:07:23", "latest_commit": "2023-09-02 17:23:50", "languages": [ @@ -937,13 +853,27 @@ ], "model_or_dataset": "model" }, + { + "description": "This is a Japanese sentence-LUKE model.", + "url": "https://huggingface.co/sonoisa/sentence-luke-japanese-base-lite", + "project_name": "sentence-luke-japanese-base-lite", + "downloads": 63740, + "source": "Hugging Face", + "score": 0.5831645446096616, + "first_commit": "2023-03-19 14:44:42", + "latest_commit": "2023-03-20 01:32:34", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "LukeModel" + }, { "description": "vibrato: Viterbi-based accelerated tokenizer", "url": "https://github.com/daac-tools/vibrato", "project_name": "vibrato", "stargazers_count": 311, "source": "GitHub", - "score": 0.5743714700107442, + "score": 0.5782294984398492, "first_commit": "2022-07-06 17:50:53", "latest_commit": "2024-05-30 19:17:07", "languages": [ @@ -952,13 +882,27 @@ ], "model_or_dataset": null }, + { + "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", + "url": "https://huggingface.co/tokyotech-llm/Swallow-7b-instruct-hf", + "project_name": "Swallow-7b-instruct-hf", + "downloads": 61889, + "source": "Hugging Face", + "score": 0.5635347811669077, + "first_commit": "2023-12-07 02:18:36", + "latest_commit": "2024-06-29 08:56:26", + "languages": [], + "model_or_dataset": "model", + "model_size": 6.83, + "model_architectures": "LlamaForCausalLM" + }, { "description": "The purpose of this repository is to make prototypes as case study in the context of proof of concept(PoC) and research and development(R&D) that I have written in my website. The main research topics are Auto-Encoders in relation to the representation learning, the statistical machine learning for energy-based models, adversarial generation net…", "url": "https://github.com/accel-brain/accel-brain-code", "project_name": "accel-brain-code", "stargazers_count": 305, "source": "GitHub", - "score": 0.5567822179351575, + "score": 0.5605893750722309, "first_commit": "2016-01-26 21:16:08", "latest_commit": "2023-12-26 12:01:37", "languages": [ @@ -975,7 +919,7 @@ "project_name": "jaconv", "stargazers_count": 299, "source": "GitHub", - "score": 0.5391929658595708, + "score": 0.5429492517046127, "first_commit": "2014-03-22 20:09:24", "latest_commit": "2024-08-13 14:26:29", "languages": [ @@ -983,13 +927,27 @@ ], "model_or_dataset": null }, + { + "description": "shisa-gamma-7b-v1 For more information see our main Shisa 7B model We applied a version of our fine-tune data set onto Japanese Stable LM Base Gamma 7B and it performed pretty well, just sharing since it might be of interest.", + "url": "https://huggingface.co/augmxnt/shisa-gamma-7b-v1", + "project_name": "shisa-gamma-7b-v1", + "downloads": 58892, + "source": "Hugging Face", + "score": 0.5317517444095151, + "first_commit": "2023-12-23 20:21:44", + "latest_commit": "2024-05-19 06:07:36", + "languages": [], + "model_or_dataset": "model", + "model_size": 7.24, + "model_architectures": "MistralForCausalLM" + }, { "description": "Japanese and Chinese dictionaries for Yomitan.", "url": "https://github.com/marvnc/yomitan-dictionaries", "project_name": "yomitan-dictionaries", "stargazers_count": 295, "source": "GitHub", - "score": 0.5274667978091796, + "score": 0.531189169459534, "first_commit": "2022-08-07 01:28:52", "latest_commit": "2024-08-04 01:00:08", "languages": [ @@ -1003,7 +961,7 @@ "project_name": "JGLUE", "stargazers_count": 294, "source": "GitHub", - "score": 0.5245352557965818, + "score": 0.5282491488982642, "first_commit": "2022-05-27 13:35:39", "latest_commit": "2023-06-24 10:50:30", "languages": [ @@ -1012,32 +970,18 @@ "model_or_dataset": null }, { - "description": "FuguMT", - "url": "https://huggingface.co/staka/fugumt-en-ja", - "project_name": "fugumt-en-ja", - "downloads": 40665, + "description": "Sentence BERT base Japanese model This repository contains a Sentence BERT base model for Japanese.", + "url": "https://huggingface.co/colorfulscoop/sbert-base-ja", + "project_name": "sbert-base-ja", + "downloads": 57843, "source": "Hugging Face", - "score": 0.5244564224951384, - "first_commit": "2022-05-08 04:23:57", - "latest_commit": "2023-08-15 17:45:04", + "score": 0.5206271512969008, + "first_commit": "2021-08-01 04:12:28", + "latest_commit": "2021-08-08 15:47:42", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "MarianMTModel" - }, - { - "description": "FuguMT", - "url": "https://huggingface.co/staka/fugumt-ja-en", - "project_name": "fugumt-ja-en", - "downloads": 40520, - "source": "Hugging Face", - "score": 0.5221782757744768, - "first_commit": "2022-05-08 04:32:09", - "latest_commit": "2023-08-15 17:40:58", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "MarianMTModel" + "model_architectures": "BertModel" }, { "description": "SudachiPy 0.6* and above are developed as Sudachi.rs.", @@ -1045,7 +989,7 @@ "project_name": "sudachi.rs", "stargazers_count": 290, "source": "GitHub", - "score": 0.5128090877461906, + "score": 0.5164890666531854, "first_commit": "2019-11-23 21:06:49", "latest_commit": "2024-06-28 10:11:04", "languages": [ @@ -1060,7 +1004,7 @@ "project_name": "Poricom", "stargazers_count": 283, "source": "GitHub", - "score": 0.49228829365800614, + "score": 0.4959089227242975, "first_commit": "2021-08-31 16:21:12", "latest_commit": "2023-06-04 18:55:23", "languages": [ @@ -1074,7 +1018,7 @@ "project_name": "japanese-stable-diffusion", "stargazers_count": 280, "source": "GitHub", - "score": 0.4834936676202128, + "score": 0.4870888610404884, "first_commit": "2022-09-09 10:11:41", "latest_commit": "2023-03-20 08:21:57", "languages": [ @@ -1083,27 +1027,13 @@ ], "model_or_dataset": null }, - { - "description": "Model Card for Japanese DeBERTa V2 base Model description This is a Japanese DeBERTa V2 base model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.", - "url": "https://huggingface.co/ku-nlp/deberta-v2-base-japanese", - "project_name": "deberta-v2-base-japanese", - "downloads": 37921, - "source": "Hugging Face", - "score": 0.48134445972620665, - "first_commit": "2023-01-05 08:04:14", - "latest_commit": "2023-05-12 14:13:03", - "languages": [], - "model_or_dataset": "model", - "model_size": 0.137, - "model_architectures": "DebertaV2ForMaskedLM" - }, { "description": "Japanese to romaji converter in Python", "url": "https://github.com/polm/cutlet", "project_name": "cutlet", "stargazers_count": 278, "source": "GitHub", - "score": 0.4776305835950172, + "score": 0.48120881991794895, "first_commit": "2020-04-16 22:59:42", "latest_commit": "2024-06-28 00:40:28", "languages": [ @@ -1118,7 +1048,7 @@ "project_name": "corvusskk", "stargazers_count": 277, "source": "GitHub", - "score": 0.4746990415824194, + "score": 0.47826879935667926, "first_commit": "2012-06-15 14:12:35", "latest_commit": "2024-08-04 19:22:13", "languages": [ @@ -1134,7 +1064,7 @@ "project_name": "llm-book", "stargazers_count": 273, "source": "GitHub", - "score": 0.46297287353202826, + "score": 0.46650871711160047, "first_commit": "2023-07-13 16:50:00", "latest_commit": "2024-07-27 21:21:13", "languages": [ @@ -1142,41 +1072,13 @@ ], "model_or_dataset": null }, - { - "description": "ELYZA-japanese-Llama-2-7b Model Description ELYZA-japanese-Llama-2-7b は、 Llama2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。 ", - "url": "https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b-instruct", - "project_name": "ELYZA-japanese-Llama-2-7b-instruct", - "downloads": 36674, - "source": "Hugging Face", - "score": 0.46175239792851797, - "first_commit": "2023-08-28 12:58:25", - "latest_commit": "2023-08-29 03:46:15", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LlamaForCausalLM" - }, - { - "description": "hotchpotch/japanese-reranker-cross-encoder-xsmall-v1 日本語で学習させた Reranker (CrossEncoder) シリーズです。 ", - "url": "https://huggingface.co/hotchpotch/japanese-reranker-cross-encoder-xsmall-v1", - "project_name": "japanese-reranker-cross-encoder-xsmall-v1", - "downloads": 36590, - "source": "Hugging Face", - "score": 0.4604326439662037, - "first_commit": "2024-03-28 04:29:26", - "latest_commit": "2024-06-10 03:57:05", - "languages": [], - "model_or_dataset": "model", - "model_size": 0.107, - "model_architectures": "XLMRobertaForSequenceClassification" - }, { "description": "Restaurant Search System through Dialogue in Japanese.", "url": "https://github.com/Hironsan/HotPepperGourmetDialogue", "project_name": "HotPepperGourmetDialogue", "stargazers_count": 272, "source": "GitHub", - "score": 0.4600413315194305, + "score": 0.4635686965503308, "first_commit": "2016-02-13 11:37:07", "latest_commit": "2016-05-19 13:05:29", "languages": [ @@ -1190,7 +1092,7 @@ "project_name": "tacotron2-japanese", "stargazers_count": 269, "source": "GitHub", - "score": 0.4512467054816371, + "score": 0.4547486348665217, "first_commit": "2022-07-25 11:42:50", "latest_commit": "2022-09-04 12:57:11", "languages": [ @@ -1205,7 +1107,7 @@ "project_name": "neologdn", "stargazers_count": 267, "source": "GitHub", - "score": 0.44538362145644156, + "score": 0.44886859374398225, "first_commit": "2015-07-22 01:15:07", "latest_commit": "2024-05-03 00:56:43", "languages": [ @@ -1216,17 +1118,45 @@ "model_or_dataset": null }, { - "description": "Llama-3-ELYZA-JP-8B Model Description Llama-3-ELYZA-JP-8B is a large language model trained by ELYZA, Inc.", - "url": "https://huggingface.co/elyza/Llama-3-ELYZA-JP-8B", - "project_name": "Llama-3-ELYZA-JP-8B", - "downloads": 34612, + "description": "FuguMT", + "url": "https://huggingface.co/staka/fugumt-en-ja", + "project_name": "fugumt-en-ja", + "downloads": 50872, "source": "Hugging Face", - "score": 0.4293555804250423, - "first_commit": "2024-06-25 06:32:13", - "latest_commit": "2024-06-26 02:56:23", + "score": 0.44670004110811756, + "first_commit": "2022-05-08 04:23:57", + "latest_commit": "2023-08-15 17:45:04", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, + "model_size": null, + "model_architectures": "MarianMTModel" + }, + { + "description": "FuguMT", + "url": "https://huggingface.co/staka/fugumt-ja-en", + "project_name": "fugumt-ja-en", + "downloads": 50408, + "source": "Hugging Face", + "score": 0.44177934405925867, + "first_commit": "2022-05-08 04:32:09", + "latest_commit": "2023-08-15 17:40:58", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "MarianMTModel" + }, + { + "description": "ELYZA-japanese-Llama-2-7b Model Description ELYZA-japanese-Llama-2-7b は、 Llama2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。 ", + "url": "https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b-instruct", + "project_name": "ELYZA-japanese-Llama-2-7b-instruct", + "downloads": 46400, + "source": "Hugging Face", + "score": 0.3992747023096326, + "first_commit": "2023-08-28 12:58:25", + "latest_commit": "2023-08-29 03:46:15", + "languages": [], + "model_or_dataset": "model", + "model_size": null, "model_architectures": "LlamaForCausalLM" }, { @@ -1235,7 +1165,7 @@ "project_name": "bert-book", "stargazers_count": 250, "source": "GitHub", - "score": 0.39554740724227916, + "score": 0.39888824420239727, "first_commit": "2021-02-04 22:11:11", "latest_commit": "2024-02-13 13:36:21", "languages": [ @@ -1249,7 +1179,7 @@ "project_name": "azooKey", "stargazers_count": 247, "source": "GitHub", - "score": 0.3867527812044858, + "score": 0.39006818251858816, "first_commit": "2020-09-03 16:35:44", "latest_commit": "2024-07-04 11:03:08", "languages": [ @@ -1264,7 +1194,7 @@ "project_name": "pdf-translator", "stargazers_count": 245, "source": "GitHub", - "score": 0.3808896971792902, + "score": 0.3841881413960488, "first_commit": "2023-04-17 14:55:03", "latest_commit": "2024-05-07 16:25:33", "languages": [ @@ -1278,7 +1208,7 @@ "project_name": "japanese-dialog-transformers", "stargazers_count": 240, "source": "GitHub", - "score": 0.36623198711630134, + "score": 0.36948803858970025, "first_commit": "2021-09-17 22:13:57", "latest_commit": "2023-06-21 09:24:35", "languages": [ @@ -1292,7 +1222,7 @@ "project_name": "namedivider-python", "stargazers_count": 237, "source": "GitHub", - "score": 0.357437361078508, + "score": 0.36066797690589114, "first_commit": "2020-11-08 00:41:44", "latest_commit": "2024-05-03 15:28:00", "languages": [ @@ -1306,7 +1236,7 @@ "project_name": "mecab", "stargazers_count": 232, "source": "GitHub", - "score": 0.34277965101551905, + "score": 0.3459678740995426, "first_commit": "2011-10-15 15:16:30", "latest_commit": "2024-05-30 20:11:11", "languages": [ @@ -1326,7 +1256,7 @@ "project_name": "nlplot", "stargazers_count": 232, "source": "GitHub", - "score": 0.34277965101551905, + "score": 0.3459678740995426, "first_commit": "2020-05-07 00:10:04", "latest_commit": "2022-09-21 23:19:20", "languages": [ @@ -1341,7 +1271,7 @@ "project_name": "vime", "stargazers_count": 228, "source": "GitHub", - "score": 0.3310534829651279, + "score": 0.3342077918544638, "first_commit": "2022-12-03 22:32:24", "latest_commit": "2022-12-03 22:32:24", "languages": [ @@ -1349,27 +1279,13 @@ ], "model_or_dataset": null }, - { - "description": "rinna/japanese-clip-vit-b-16", - "url": "https://huggingface.co/rinna/japanese-clip-vit-b-16", - "project_name": "japanese-clip-vit-b-16", - "downloads": 28212, - "source": "Hugging Face", - "score": 0.3288028975820529, - "first_commit": "2022-04-27 07:52:33", - "latest_commit": "2024-07-20 08:42:32", - "languages": [], - "model_or_dataset": "model", - "model_size": 0.197, - "model_architectures": "CLIPModel" - }, { "description": "A lexicon for Sudachi", "url": "https://github.com/WorksApplications/SudachiDict", "project_name": "SudachiDict", "stargazers_count": 225, "source": "GitHub", - "score": 0.3222588569273345, + "score": 0.3253877301706547, "first_commit": "2019-04-01 17:14:39", "latest_commit": "2024-07-19 18:45:35", "languages": [ @@ -1384,7 +1300,7 @@ "project_name": "Jitendex", "stargazers_count": 225, "source": "GitHub", - "score": 0.3222588569273345, + "score": 0.3253877301706547, "first_commit": "2023-10-09 17:45:11", "latest_commit": "2024-07-09 16:43:23", "languages": [], @@ -1396,7 +1312,7 @@ "project_name": "konoha", "stargazers_count": 224, "source": "GitHub", - "score": 0.31932731491473676, + "score": 0.322447709609385, "first_commit": "2018-08-22 13:55:37", "latest_commit": "2024-05-16 00:01:37", "languages": [ @@ -1411,7 +1327,7 @@ "project_name": "vaporetto", "stargazers_count": 223, "source": "GitHub", - "score": 0.31639577290213894, + "score": 0.3195076890481153, "first_commit": "2021-08-18 22:59:40", "latest_commit": "2024-07-14 16:33:38", "languages": [ @@ -1419,13 +1335,41 @@ ], "model_or_dataset": null }, + { + "description": "Model Card for Japanese DeBERTa V2 base Model description This is a Japanese DeBERTa V2 base model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.", + "url": "https://huggingface.co/ku-nlp/deberta-v2-base-japanese", + "project_name": "deberta-v2-base-japanese", + "downloads": 38625, + "source": "Hugging Face", + "score": 0.31682121188963686, + "first_commit": "2023-01-05 08:04:14", + "latest_commit": "2023-05-12 14:13:03", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.137, + "model_architectures": "DebertaV2ForMaskedLM" + }, + { + "description": "Llama-3-ELYZA-JP-8B Model Description Llama-3-ELYZA-JP-8B is a large language model trained by ELYZA, Inc.", + "url": "https://huggingface.co/elyza/Llama-3-ELYZA-JP-8B", + "project_name": "Llama-3-ELYZA-JP-8B", + "downloads": 38336, + "source": "Hugging Face", + "score": 0.31375638118463633, + "first_commit": "2024-06-25 06:32:13", + "latest_commit": "2024-06-26 02:56:23", + "languages": [], + "model_or_dataset": "model", + "model_size": 8.03, + "model_architectures": "LlamaForCausalLM" + }, { "description": "Building AI-based conversational avatars lightning fast", "url": "https://github.com/uezo/aiavatarkit", "project_name": "aiavatarkit", "stargazers_count": 218, "source": "GitHub", - "score": 0.30173806283915, + "score": 0.3048075862417668, "first_commit": "2023-05-27 23:14:32", "latest_commit": "2024-06-08 17:55:22", "languages": [ @@ -1433,13 +1377,27 @@ ], "model_or_dataset": null }, + { + "description": "hotchpotch/japanese-reranker-cross-encoder-xsmall-v1 日本語で学習させた Reranker (CrossEncoder) シリーズです。 ", + "url": "https://huggingface.co/hotchpotch/japanese-reranker-cross-encoder-xsmall-v1", + "project_name": "japanese-reranker-cross-encoder-xsmall-v1", + "downloads": 37128, + "source": "Hugging Face", + "score": 0.30094560093674505, + "first_commit": "2024-03-28 04:29:26", + "latest_commit": "2024-06-10 03:57:05", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.107, + "model_architectures": "XLMRobertaForSequenceClassification" + }, { "description": "日本語OCR", "url": "https://github.com/tanreinama/OCR_Japanease", "project_name": "OCR_Japanease", "stargazers_count": 216, "source": "GitHub", - "score": 0.2958749788139544, + "score": 0.29892754511922737, "first_commit": "2020-04-08 09:25:03", "latest_commit": "2021-04-30 19:26:24", "languages": [ @@ -1447,13 +1405,27 @@ ], "model_or_dataset": null }, + { + "description": "JMTEB:", + "url": "https://huggingface.co/datasets/sbintuitions/JMTEB", + "project_name": "JMTEB", + "downloads": 36325, + "source": "Hugging Face", + "score": 0.29242982565606895, + "first_commit": "2024-02-22 18:15:27", + "latest_commit": "2024-06-28 15:18:20", + "languages": [], + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null + }, { "description": "Yet another Japanese IME for IBus/Linux", "url": "https://github.com/akaza-im/akaza", "project_name": "akaza", "stargazers_count": 212, "source": "GitHub", - "score": 0.2841488107635633, + "score": 0.28716746287414857, "first_commit": "2020-09-03 01:11:08", "latest_commit": "2023-05-28 23:41:07", "languages": [ @@ -1469,7 +1441,7 @@ "project_name": "jtubespeech", "stargazers_count": 208, "source": "GitHub", - "score": 0.2724226427131721, + "score": 0.2754073806290697, "first_commit": "2021-07-01 00:11:55", "latest_commit": "2023-03-02 15:50:30", "languages": [ @@ -1477,55 +1449,13 @@ ], "model_or_dataset": "dataset" }, - { - "description": "llm-book/bert-base-japanese-v3-ner-wikipedia-dataset 「大規模言語モデル入門」の第6章で紹介している固有表現認識のモデルです。 ", - "url": "https://huggingface.co/llm-book/bert-base-japanese-v3-ner-wikipedia-dataset", - "project_name": "bert-base-japanese-v3-ner-wikipedia-dataset", - "downloads": 24420, - "source": "Hugging Face", - "score": 0.26922543299758167, - "first_commit": "2023-05-28 08:06:41", - "latest_commit": "2023-07-25 13:32:15", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForTokenClassification" - }, - { - "description": "License:CreativeML Open RAIL-M Additional Copyright: sazyou_roukaku (TwitterID @sazyou_roukaku) as of May 31, 2023 このモデルは『CreativeML Open RAIL-M』でLicenseそのものに変更はありません。 ", - "url": "https://huggingface.co/sazyou-roukaku/BracingEvoMix", - "project_name": "BracingEvoMix", - "downloads": 24132, - "source": "Hugging Face", - "score": 0.26470056226964717, - "first_commit": "2023-05-31 10:29:16", - "latest_commit": "2023-10-01 08:58:54", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": null - }, - { - "description": "LaBSE Model description Language-agnostic BERT Sentence Encoder (LaBSE) is a BERT-based model trained for sentence embedding for 109 languages.", - "url": "https://huggingface.co/setu4993/LaBSE", - "project_name": "LaBSE", - "downloads": 23620, - "source": "Hugging Face", - "score": 0.256656347642208, - "first_commit": "2021-01-11 06:06:51", - "latest_commit": "2023-10-18 23:23:16", - "languages": [], - "model_or_dataset": "model", - "model_size": 0.47100000000000003, - "model_architectures": "BertModel" - }, { "description": "Tutorial to train fastText with Japanese corpus", "url": "https://github.com/icoxfog417/fastTextJapaneseTutorial", "project_name": "fastTextJapaneseTutorial", "stargazers_count": 202, "source": "GitHub", - "score": 0.2548333906375854, + "score": 0.2577672572614515, "first_commit": "2016-09-28 13:06:13", "latest_commit": "2016-09-29 14:21:51", "languages": [ @@ -1539,7 +1469,7 @@ "project_name": "posuto", "stargazers_count": 200, "source": "GitHub", - "score": 0.24897030661238984, + "score": 0.25188721613891213, "first_commit": null, "latest_commit": null, "languages": [], @@ -1551,7 +1481,7 @@ "project_name": "kytea", "stargazers_count": 199, "source": "GitHub", - "score": 0.24603876459979207, + "score": 0.24894719557764242, "first_commit": "2011-03-03 14:53:14", "latest_commit": "2020-04-03 09:46:01", "languages": [ @@ -1561,27 +1491,13 @@ ], "model_or_dataset": null }, - { - "description": "Please feel free to open an issue or pull request.", - "url": "https://huggingface.co/datasets/shunk031/JGLUE", - "project_name": "JGLUE", - "downloads": 22917, - "source": "Hugging Face", - "score": 0.24561126388617338, - "first_commit": "2023-02-25 13:33:13", - "latest_commit": "2024-05-21 11:23:51", - "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null - }, { "description": "Python wrapper for OpenJTalk", "url": "https://github.com/r9y9/pyopenjtalk", "project_name": "pyopenjtalk", "stargazers_count": 192, "source": "GitHub", - "score": 0.22551797051160755, + "score": 0.22836705164875448, "first_commit": "2018-08-07 00:37:37", "latest_commit": "2024-07-13 16:04:09", "languages": [ @@ -1596,7 +1512,7 @@ "project_name": "daachorse", "stargazers_count": 192, "source": "GitHub", - "score": 0.22551797051160755, + "score": 0.22836705164875448, "first_commit": "2021-09-02 11:37:02", "latest_commit": "2024-06-06 18:11:39", "languages": [ @@ -1605,18 +1521,18 @@ "model_or_dataset": null }, { - "description": "nlp-waseda/roberta-base-japanese-with-auto-jumanpp Model description", - "url": "https://huggingface.co/nlp-waseda/roberta-base-japanese-with-auto-jumanpp", - "project_name": "roberta-base-japanese-with-auto-jumanpp", - "downloads": 21223, + "description": "llm-book/bert-base-japanese-v3-ner-wikipedia-dataset 「大規模言語モデル入門」の第6章で紹介している固有表現認識のモデルです。 ", + "url": "https://huggingface.co/llm-book/bert-base-japanese-v3-ner-wikipedia-dataset", + "project_name": "bert-base-japanese-v3-ner-wikipedia-dataset", + "downloads": 29838, "source": "Hugging Face", - "score": 0.21899622564616963, - "first_commit": "2022-10-15 05:09:36", - "latest_commit": "2022-10-21 10:57:40", + "score": 0.22363551152687125, + "first_commit": "2023-05-28 08:06:41", + "latest_commit": "2023-07-25 13:32:15", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "RobertaForMaskedLM" + "model_architectures": "BertForTokenClassification" }, { "description": "English-Japanese Dictionary data (Public Domain) EJDict-hand", @@ -1624,7 +1540,7 @@ "project_name": "EJDict", "stargazers_count": 189, "source": "GitHub", - "score": 0.2167233444738142, + "score": 0.21954698996494537, "first_commit": "2016-01-04 23:23:52", "latest_commit": "2024-02-15 09:49:00", "languages": [ @@ -1638,7 +1554,7 @@ "project_name": "kanjitomo-ocr", "stargazers_count": 184, "source": "GitHub", - "score": 0.20206563441082526, + "score": 0.20484688715859686, "first_commit": "2019-12-08 14:09:53", "latest_commit": "2021-05-03 21:38:06", "languages": [ @@ -1653,7 +1569,7 @@ "project_name": "bunkai", "stargazers_count": 181, "source": "GitHub", - "score": 0.1932710083730319, + "score": 0.19602682547478775, "first_commit": "2021-04-21 12:36:10", "latest_commit": "2023-08-10 14:13:25", "languages": [ @@ -1667,7 +1583,7 @@ "project_name": "ita-corpus", "stargazers_count": 178, "source": "GitHub", - "score": 0.18447638233523853, + "score": 0.18720676379097864, "first_commit": "2021-06-03 11:22:38", "latest_commit": "2023-12-04 00:50:44", "languages": [], @@ -1679,7 +1595,7 @@ "project_name": "elasticsearch-sudachi", "stargazers_count": 177, "source": "GitHub", - "score": 0.18154484032264073, + "score": 0.18426674322970893, "first_commit": "2017-11-09 19:21:47", "latest_commit": "2024-07-04 14:46:30", "languages": [ @@ -1689,13 +1605,27 @@ ], "model_or_dataset": null }, + { + "description": "BERT base Japanese (character-level tokenization with whole word masking, CC-100 and jawiki-20230102)", + "url": "https://huggingface.co/tohoku-nlp/bert-base-japanese-char-v3", + "project_name": "bert-base-japanese-char-v3", + "downloads": 25661, + "source": "Hugging Face", + "score": 0.17933863313660472, + "first_commit": "2023-05-19 00:33:09", + "latest_commit": "2023-05-19 00:39:44", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "BertForPreTraining" + }, { "description": "Topologically ordered lists of kanji for effective learning", "url": "https://github.com/scriptin/topokanji", "project_name": "topokanji", "stargazers_count": 174, "source": "GitHub", - "score": 0.17275021428484738, + "score": 0.17544668154589982, "first_commit": "2015-05-18 01:55:58", "latest_commit": "2016-01-24 05:18:22", "languages": [ @@ -1703,13 +1633,27 @@ ], "model_or_dataset": "dataset" }, + { + "description": "rinna/japanese-clip-vit-b-16", + "url": "https://huggingface.co/rinna/japanese-clip-vit-b-16", + "project_name": "japanese-clip-vit-b-16", + "downloads": 25053, + "source": "Hugging Face", + "score": 0.17289082321051377, + "first_commit": "2022-04-27 07:52:33", + "latest_commit": "2024-07-20 08:42:32", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.197, + "model_architectures": "CLIPModel" + }, { "description": "Can neural networks transliterate Romaji into Japanese correctly?", "url": "https://github.com/Kyubyong/neural_japanese_transliterator", "project_name": "neural_japanese_transliterator", "stargazers_count": 173, "source": "GitHub", - "score": 0.1698186722722496, + "score": 0.17250666098463013, "first_commit": "2017-01-01 13:20:54", "latest_commit": "2017-09-17 15:21:27", "languages": [ @@ -1723,7 +1667,7 @@ "project_name": "summarize_arxv", "stargazers_count": 173, "source": "GitHub", - "score": 0.1698186722722496, + "score": 0.17250666098463013, "first_commit": "2023-05-21 17:03:22", "latest_commit": "2023-05-23 01:54:10", "languages": [ @@ -1732,18 +1676,32 @@ "model_or_dataset": null }, { - "description": "このドキュメントの日本語版はまだ作成中です。", - "url": "https://huggingface.co/bclavie/JaColBERT", - "project_name": "JaColBERT", - "downloads": 17769, + "description": "十条蛍（Hotaru Jujo）の作成したLoRAを配布しています。 ", + "url": "https://huggingface.co/JujoHotaru/lora", + "project_name": "lora", + "downloads": 23810, "source": "Hugging Face", - "score": 0.1647291996243438, - "first_commit": "2023-12-25 22:43:54", - "latest_commit": "2024-01-27 15:30:00", + "score": 0.15970886969385079, + "first_commit": null, + "latest_commit": null, "languages": [], "model_or_dataset": "model", - "model_size": 0.111, - "model_architectures": "HF_ColBERT" + "model_size": null, + "model_architectures": null + }, + { + "description": "nlp-waseda/roberta-base-japanese-with-auto-jumanpp Model description", + "url": "https://huggingface.co/nlp-waseda/roberta-base-japanese-with-auto-jumanpp", + "project_name": "roberta-base-japanese-with-auto-jumanpp", + "downloads": 23541, + "source": "Hugging Face", + "score": 0.15685613799957698, + "first_commit": "2022-10-15 05:09:36", + "latest_commit": "2022-10-21 10:57:40", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "RobertaForMaskedLM" }, { "description": "国会議案データベース：衆議院", @@ -1751,7 +1709,7 @@ "project_name": "house-of-representatives", "stargazers_count": 167, "source": "GitHub", - "score": 0.15222942019666288, + "score": 0.1548665376170119, "first_commit": "2022-04-18 14:41:05", "latest_commit": "2024-08-15 14:09:44", "languages": [ @@ -1766,7 +1724,7 @@ "project_name": "jmdict-simplified", "stargazers_count": 166, "source": "GitHub", - "score": 0.1492978781840651, + "score": 0.1519265170557422, "first_commit": "2016-02-07 00:30:44", "latest_commit": "2024-08-12 12:21:03", "languages": [ @@ -1777,18 +1735,32 @@ "model_or_dataset": "dataset" }, { - "description": "LINE DistilBERT Japanese This is a DistilBERT model pre-trained on 131 GB of Japanese web text.", - "url": "https://huggingface.co/line-corporation/line-distilbert-base-japanese", - "project_name": "line-distilbert-base-japanese", - "downloads": 15911, + "description": "BERT base Japanese (unidic-lite with whole word masking, CC-100 and jawiki-20230102)", + "url": "https://huggingface.co/tohoku-nlp/bert-base-japanese-v3", + "project_name": "bert-base-japanese-v3", + "downloads": 22758, "source": "Hugging Face", - "score": 0.13553749888648844, - "first_commit": "2023-03-10 10:23:54", - "latest_commit": "2023-12-01 09:50:34", + "score": 0.14855246172962758, + "first_commit": "2023-05-19 00:13:53", + "latest_commit": "2023-05-19 00:31:53", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DistilBertForMaskedLM" + "model_architectures": "BertForPreTraining" + }, + { + "description": "License:CreativeML Open RAIL-M Additional Copyright: sazyou_roukaku (TwitterID @sazyou_roukaku) as of May 31, 2023 このモデルは『CreativeML Open RAIL-M』でLicenseそのものに変更はありません。 ", + "url": "https://huggingface.co/sazyou-roukaku/BracingEvoMix", + "project_name": "BracingEvoMix", + "downloads": 21934, + "source": "Hugging Face", + "score": 0.13981398248768848, + "first_commit": "2023-05-31 10:29:16", + "latest_commit": "2023-10-01 08:58:54", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": null }, { "description": "ディープラーニングモデルの性能を体系的に最大化するためのプレイブック", @@ -1796,7 +1768,7 @@ "project_name": "tuning_playbook_ja", "stargazers_count": 161, "source": "GitHub", - "score": 0.13464016812107615, + "score": 0.1372264142493937, "first_commit": "2023-01-22 02:19:42", "latest_commit": "2023-01-22 22:10:48", "languages": [], @@ -1808,7 +1780,7 @@ "project_name": "DistilBERT-base-jp", "stargazers_count": 160, "source": "GitHub", - "score": 0.13170862610847836, + "score": 0.13428639368812398, "first_commit": "2020-04-22 16:17:15", "latest_commit": "2020-04-22 16:24:26", "languages": [], @@ -1820,7 +1792,7 @@ "project_name": "inappropriate-words-ja", "stargazers_count": 159, "source": "GitHub", - "score": 0.12877708409588057, + "score": 0.13134637312685427, "first_commit": "2020-08-17 13:38:34", "latest_commit": "2021-12-02 00:33:00", "languages": [ @@ -1834,7 +1806,7 @@ "project_name": "JapaneseEmbeddingEval", "stargazers_count": 157, "source": "GitHub", - "score": 0.12291400007068501, + "score": 0.12546633200431487, "first_commit": "2023-01-07 13:35:18", "latest_commit": "2024-04-06 12:45:12", "languages": [ @@ -1848,7 +1820,7 @@ "project_name": "Jotoba", "stargazers_count": 157, "source": "GitHub", - "score": 0.12291400007068501, + "score": 0.12546633200431487, "first_commit": "2021-04-15 11:08:23", "latest_commit": "2024-01-22 17:06:42", "languages": [ @@ -1858,32 +1830,18 @@ "model_or_dataset": null }, { - "description": "Llama3 Swallow", - "url": "https://huggingface.co/tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1", - "project_name": "Llama-3-Swallow-8B-Instruct-v0.1", - "downloads": 14950, - "source": "Hugging Face", - "score": 0.1204388851033458, - "first_commit": "2024-06-26 04:11:25", - "latest_commit": "2024-07-06 15:02:39", - "languages": [], - "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": "LlamaForCausalLM" - }, - { - "description": "Japanese Stable LM Base Gamma 7B Model Description", - "url": "https://huggingface.co/stabilityai/japanese-stablelm-base-gamma-7b", - "project_name": "japanese-stablelm-base-gamma-7b", - "downloads": 14177, + "description": "LaBSE Model description Language-agnostic BERT Sentence Encoder (LaBSE) is a BERT-based model trained for sentence embedding for 109 languages.", + "url": "https://huggingface.co/setu4993/LaBSE", + "project_name": "LaBSE", + "downloads": 20114, "source": "Hugging Face", - "score": 0.10829400637871597, - "first_commit": "2023-10-16 08:15:14", - "latest_commit": "2024-01-25 08:05:12", + "score": 0.12051297251156086, + "first_commit": "2021-01-11 06:06:51", + "latest_commit": "2023-10-18 23:23:16", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": "MistralForCausalLM" + "model_size": 0.47100000000000003, + "model_architectures": "BertModel" }, { "description": "Japanese negative positive classification.日本語文書のネガポジを判定。", @@ -1891,7 +1849,7 @@ "project_name": "negapoji", "stargazers_count": 151, "source": "GitHub", - "score": 0.10532474799509828, + "score": 0.10782620863669665, "first_commit": "2017-08-17 17:23:49", "latest_commit": "2017-08-20 18:12:51", "languages": [ @@ -1905,7 +1863,7 @@ "project_name": "dictation-kit", "stargazers_count": 151, "source": "GitHub", - "score": 0.10532474799509828, + "score": 0.10782620863669665, "first_commit": "2015-10-03 17:08:52", "latest_commit": "2019-04-18 11:41:47", "languages": [ @@ -1920,7 +1878,7 @@ "project_name": "chiVe", "stargazers_count": 151, "source": "GitHub", - "score": 0.10532474799509828, + "score": 0.10782620863669665, "first_commit": "2019-11-18 15:39:08", "latest_commit": "2024-03-01 17:50:40", "languages": [ @@ -1928,27 +1886,13 @@ ], "model_or_dataset": "model" }, - { - "description": "BERT base Japanese (character-level tokenization with whole word masking, CC-100 and jawiki-20230102)", - "url": "https://huggingface.co/tohoku-nlp/bert-base-japanese-char-v3", - "project_name": "bert-base-japanese-char-v3", - "downloads": 13869, - "source": "Hugging Face", - "score": 0.10345490851689712, - "first_commit": "2023-05-19 00:33:09", - "latest_commit": "2023-05-19 00:39:44", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForPreTraining" - }, { "description": "Phishing URL dataset from JPCERT/CC", "url": "https://github.com/JPCERTCC/phishurl-list", "project_name": "phishurl-list", "stargazers_count": 150, "source": "GitHub", - "score": 0.1023932059825005, + "score": 0.10488618807542695, "first_commit": "2022-08-05 15:20:50", "latest_commit": "2024-05-02 04:51:47", "languages": [ @@ -1956,13 +1900,41 @@ ], "model_or_dataset": "dataset" }, + { + "description": "このドキュメントの日本語版はまだ作成中です。", + "url": "https://huggingface.co/bclavie/JaColBERT", + "project_name": "JaColBERT", + "downloads": 18086, + "source": "Hugging Face", + "score": 0.0990061328238758, + "first_commit": "2023-12-25 22:43:54", + "latest_commit": "2024-01-27 15:30:00", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.111, + "model_architectures": "HF_ColBERT" + }, + { + "description": "Please feel free to open an issue or pull request.", + "url": "https://huggingface.co/datasets/shunk031/JGLUE", + "project_name": "JGLUE", + "downloads": 18026, + "source": "Hugging Face", + "score": 0.09836983579169577, + "first_commit": "2023-02-25 13:33:13", + "latest_commit": "2024-05-21 11:23:51", + "languages": [], + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null + }, { "description": "WRIME: 主観と客観の感情分析データセット", "url": "https://github.com/ids-cv/wrime", "project_name": "wrime", "stargazers_count": 145, "source": "GitHub", - "score": 0.08773549591951156, + "score": 0.09018608526907843, "first_commit": "2020-08-18 14:13:44", "latest_commit": "2023-01-15 13:44:21", "languages": [], @@ -1974,7 +1946,7 @@ "project_name": "asari", "stargazers_count": 143, "source": "GitHub", - "score": 0.08187241189431599, + "score": 0.08430604414653903, "first_commit": "2019-02-06 14:17:47", "latest_commit": "2022-10-19 07:38:31", "languages": [ @@ -1988,7 +1960,7 @@ "project_name": "wanna", "stargazers_count": 143, "source": "GitHub", - "score": 0.08187241189431599, + "score": 0.08430604414653903, "first_commit": "2023-03-01 18:10:59", "latest_commit": "2023-04-02 00:25:56", "languages": [ @@ -2002,7 +1974,7 @@ "project_name": "mojimoji", "stargazers_count": 142, "source": "GitHub", - "score": 0.0789408698817182, + "score": 0.08136602358526931, "first_commit": "2013-11-03 01:38:05", "latest_commit": "2024-01-12 19:24:55", "languages": [ @@ -2016,7 +1988,7 @@ "project_name": "jp-stable", "stargazers_count": 142, "source": "GitHub", - "score": 0.0789408698817182, + "score": 0.08136602358526931, "first_commit": null, "latest_commit": null, "languages": [], @@ -2028,7 +2000,7 @@ "project_name": "Japanese-Alpaca-LoRA", "stargazers_count": 142, "source": "GitHub", - "score": 0.0789408698817182, + "score": 0.08136602358526931, "first_commit": "2023-03-22 23:04:56", "latest_commit": "2023-04-03 05:31:02", "languages": [ @@ -2037,26 +2009,26 @@ "model_or_dataset": "model" }, { - "description": "BERT base Japanese (unidic-lite with whole word masking, jawiki-20200831)", - "url": "https://huggingface.co/tohoku-nlp/bert-base-japanese-v2", - "project_name": "bert-base-japanese-v2", - "downloads": 12115, + "description": "Contributors/Maintainers Junfeng Jiang@Aizawa Lab: jiangjf@is.s.u-tokyo.ac.jp", + "url": "https://huggingface.co/datasets/Coldog2333/JMedBench", + "project_name": "JMedBench", + "downloads": 16420, "source": "Hugging Face", - "score": 0.07589718887524033, - "first_commit": "2021-03-05 03:37:30", - "latest_commit": "2021-09-23 15:45:31", + "score": 0.0813382852303436, + "first_commit": "2024-08-17 11:12:54", + "latest_commit": "2024-09-01 12:41:40", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "BertForMaskedLM" + "model_architectures": null }, { "description": "bert-finetuned-japanese-sentiment This model is a fine-tuned version of cl-tohoku/bert-base-japanese-v2 on product amazon reviews japanese dataset.", "url": "https://huggingface.co/christian-phu/bert-finetuned-japanese-sentiment", "project_name": "bert-finetuned-japanese-sentiment", - "downloads": 12036, + "downloads": 15767, "source": "Hugging Face", - "score": 0.07465599169639718, + "score": 0.07441325253011759, "first_commit": "2023-04-06 16:43:51", "latest_commit": "2023-04-07 17:27:53", "languages": [], @@ -2064,13 +2036,41 @@ "model_size": null, "model_architectures": "BertForSequenceClassification" }, + { + "description": "Japanese Stable LM Base Gamma 7B Model Description", + "url": "https://huggingface.co/stabilityai/japanese-stablelm-base-gamma-7b", + "project_name": "japanese-stablelm-base-gamma-7b", + "downloads": 15095, + "source": "Hugging Face", + "score": 0.06728672576970124, + "first_commit": "2023-10-16 08:15:14", + "latest_commit": "2024-01-25 08:05:12", + "languages": [], + "model_or_dataset": "model", + "model_size": 7.24, + "model_architectures": "MistralForCausalLM" + }, + { + "description": "LINE DistilBERT Japanese This is a DistilBERT model pre-trained on 131 GB of Japanese web text.", + "url": "https://huggingface.co/line-corporation/line-distilbert-base-japanese", + "project_name": "line-distilbert-base-japanese", + "downloads": 14953, + "source": "Hugging Face", + "score": 0.06578082279354183, + "first_commit": "2023-03-10 10:23:54", + "latest_commit": "2023-12-01 09:50:34", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "DistilBertForMaskedLM" + }, { "description": "A set of metrics for feature selection from text data", "url": "https://github.com/Kensuke-Mitsuzawa/JapaneseTokenizers", "project_name": "JapaneseTokenizers", "stargazers_count": 136, "source": "GitHub", - "score": 0.06135161780613148, + "score": 0.0637259002176511, "first_commit": "2015-09-01 19:27:42", "latest_commit": "2019-03-25 16:52:52", "languages": [ @@ -2078,13 +2078,27 @@ ], "model_or_dataset": null }, + { + "description": "Llama3 Swallow", + "url": "https://huggingface.co/tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1", + "project_name": "Llama-3-Swallow-8B-Instruct-v0.1", + "downloads": 14295, + "source": "Hugging Face", + "score": 0.05880276534063415, + "first_commit": "2024-06-26 04:11:25", + "latest_commit": "2024-07-06 15:02:39", + "languages": [], + "model_or_dataset": "model", + "model_size": 8.03, + "model_architectures": "LlamaForCausalLM" + }, { "description": "chakki's Aspect-Based Sentiment Analysis dataset", "url": "https://github.com/chakki-works/chABSA-dataset", "project_name": "chABSA-dataset", "stargazers_count": 134, "source": "GitHub", - "score": 0.0554885337809359, + "score": 0.057845859095111696, "first_commit": "2017-12-27 11:51:01", "latest_commit": "2018-09-11 12:28:06", "languages": [ @@ -2094,13 +2108,27 @@ ], "model_or_dataset": "dataset" }, + { + "description": "BERT base Japanese (unidic-lite with whole word masking, jawiki-20200831)", + "url": "https://huggingface.co/tohoku-nlp/bert-base-japanese-v2", + "project_name": "bert-base-japanese-v2", + "downloads": 13759, + "source": "Hugging Face", + "score": 0.0531185118531592, + "first_commit": "2021-03-05 03:37:30", + "latest_commit": "2021-09-23 15:45:31", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "BertForMaskedLM" + }, { "description": "自然言語で書かれた時間情報表現を抽出/規格化するルールベースの解析器", "url": "https://github.com/yagays/ja-timex", "project_name": "ja-timex", "stargazers_count": 132, "source": "GitHub", - "score": 0.049625449755740327, + "score": 0.051965817972572284, "first_commit": "2021-07-18 20:38:04", "latest_commit": "2023-11-04 14:58:31", "languages": [ @@ -2114,7 +2142,7 @@ "project_name": "kanji-data", "stargazers_count": 130, "source": "GitHub", - "score": 0.043762365730544754, + "score": 0.04608577685003288, "first_commit": "2019-02-28 05:53:36", "latest_commit": "2019-12-29 12:12:54", "languages": [ @@ -2129,47 +2157,19 @@ "project_name": "awesome-bert-japanese", "stargazers_count": 130, "source": "GitHub", - "score": 0.043762365730544754, + "score": 0.04608577685003288, "first_commit": "2020-07-27 00:10:39", "latest_commit": "2023-03-15 18:51:20", "languages": [], "model_or_dataset": null }, - { - "description": "BERT large Japanese (unidic-lite with whole word masking, jawiki-20200831)", - "url": "https://huggingface.co/tohoku-nlp/bert-large-japanese", - "project_name": "bert-large-japanese", - "downloads": 9999, - "source": "Hugging Face", - "score": 0.042651958110276965, - "first_commit": "2021-03-05 06:17:13", - "latest_commit": "2021-09-23 15:45:41", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForMaskedLM" - }, - { - "description": "Fugaku-LLM-13B-instruct-gguf Fugaku-LLMさんが公開しているFugaku-LLM-13B-instructのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Fugaku-LLM-13B-instruct-gguf", - "project_name": "Fugaku-LLM-13B-instruct-gguf", - "downloads": 9730, - "source": "Hugging Face", - "score": 0.03842560315953256, - "first_commit": "2024-05-10 16:43:49", - "latest_commit": "2024-05-12 06:06:51", - "languages": [], - "model_or_dataset": "model", - "model_size": 13.4, - "model_architectures": null - }, { "description": "Wikipediaを用いた日本語の固有表現抽出データセット", "url": "https://github.com/stockmarkteam/ner-wikipedia-dataset", "project_name": "ner-wikipedia-dataset", "stargazers_count": 127, "source": "GitHub", - "score": 0.034967739692751396, + "score": 0.03726571516622377, "first_commit": "2020-12-15 01:52:19", "latest_commit": "2023-09-02 23:44:38", "languages": [ @@ -2183,7 +2183,7 @@ "project_name": "PAX_SAPIENTICA", "stargazers_count": 127, "source": "GitHub", - "score": 0.034967739692751396, + "score": 0.03726571516622377, "first_commit": "2022-06-24 23:18:02", "latest_commit": "2024-08-13 01:06:14", "languages": [ @@ -2199,7 +2199,7 @@ "project_name": "hepburn", "stargazers_count": 126, "source": "GitHub", - "score": 0.0320361976801536, + "score": 0.03432569460495406, "first_commit": "2013-06-28 03:06:52", "latest_commit": "2023-09-08 09:11:19", "languages": [ @@ -2207,41 +2207,13 @@ ], "model_or_dataset": null }, - { - "description": "luke-japanese-large luke-japanese is the Japanese version of LUKE (Language Understanding with Knowledge-based Embeddings), a pre-trained knowledge-enhanced contextualized representation of words and entities.", - "url": "https://huggingface.co/studio-ousia/luke-japanese-large", - "project_name": "luke-japanese-large", - "downloads": 8936, - "source": "Hugging Face", - "score": 0.025950785944324192, - "first_commit": "2022-11-07 14:25:53", - "latest_commit": "2022-11-09 11:18:56", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LukeForMaskedLM" - }, - { - "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", - "url": "https://huggingface.co/tokyotech-llm/Swallow-7b-instruct-v0.1", - "project_name": "Swallow-7b-instruct-v0.1", - "downloads": 8852, - "source": "Hugging Face", - "score": 0.024631031982009957, - "first_commit": "2024-03-04 08:46:03", - "latest_commit": "2024-07-06 15:18:14", - "languages": [], - "model_or_dataset": "model", - "model_size": 6.83, - "model_architectures": "LlamaForCausalLM" - }, { "description": "Kanji usage frequency data collected from various sources", "url": "https://github.com/scriptin/kanji-frequency", "project_name": "kanji-frequency", "stargazers_count": 123, "source": "GitHub", - "score": 0.023241571642360244, + "score": 0.025505632921144956, "first_commit": "2016-01-23 01:19:08", "latest_commit": "2024-07-13 03:51:19", "languages": [ @@ -2256,7 +2228,7 @@ "project_name": "deep-learning-with-pytorch-ja", "stargazers_count": 121, "source": "GitHub", - "score": 0.01737848761716467, + "score": 0.019625591798605548, "first_commit": "2020-12-05 15:15:16", "latest_commit": "2021-05-13 11:02:11", "languages": [ @@ -2273,7 +2245,7 @@ "project_name": "kwja", "stargazers_count": 119, "source": "GitHub", - "score": 0.011515403591969096, + "score": 0.013745550676066143, "first_commit": "2022-05-25 16:09:37", "latest_commit": "2024-08-06 23:13:59", "languages": [ @@ -2285,9 +2257,9 @@ "description": "Llama3 Swallow", "url": "https://huggingface.co/tokyotech-llm/Llama-3-Swallow-8B-v0.1", "project_name": "Llama-3-Swallow-8B-v0.1", - "downloads": 7821, + "downloads": 9617, "source": "Hugging Face", - "score": 0.008432623230272133, + "score": 0.009192806731664376, "first_commit": "2024-05-20 06:36:00", "latest_commit": "2024-07-01 06:24:48", "languages": [], @@ -2295,41 +2267,13 @@ "model_size": 8.03, "model_architectures": "LlamaForCausalLM" }, - { - "description": "Model Card for Japanese DeBERTa V3 base Model description This is a Japanese DeBERTa V3 base model pre-trained on LLM-jp corpus v1.0.", - "url": "https://huggingface.co/ku-nlp/deberta-v3-base-japanese", - "project_name": "deberta-v3-base-japanese", - "downloads": 7805, - "source": "Hugging Face", - "score": 0.00818124152316466, - "first_commit": "2024-04-23 05:08:21", - "latest_commit": "2024-04-28 06:08:55", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": null - }, - { - "description": "CyberAgentLM2-7B (CALM2-7B)", - "url": "https://huggingface.co/cyberagent/calm2-7b", - "project_name": "calm2-7b", - "downloads": 7785, - "source": "Hugging Face", - "score": 0.007867014389280317, - "first_commit": "2023-11-01 07:24:59", - "latest_commit": "2023-11-02 05:46:18", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LlamaForCausalLM" - }, { "description": "Python 3 library for manipulating Jim Breen's JMdict, KanjiDic2, JMnedict and kanji-radical mappings", "url": "https://github.com/neocl/jamdict", "project_name": "jamdict", "stargazers_count": 117, "source": "GitHub", - "score": 0.0056523195667735225, + "score": 0.007865509553526736, "first_commit": "2016-10-25 10:47:58", "latest_commit": "2021-06-06 12:04:03", "languages": [ @@ -2338,18 +2282,18 @@ "model_or_dataset": "dataset" }, { - "description": "Llama-3.1-70B-Japanese-Instruct-2407-gguf cyberagentさんが公開しているLlama-3.1-70B-Japanese-Instruct-2407のggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Llama-3.1-70B-Japanese-Instruct-2407-gguf", - "project_name": "Llama-3.1-70B-Japanese-Instruct-2407-gguf", - "downloads": 7540, + "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", + "url": "https://huggingface.co/tokyotech-llm/Swallow-7b-instruct-v0.1", + "project_name": "Swallow-7b-instruct-v0.1", + "downloads": 9260, "source": "Hugging Face", - "score": 0.00401773199919713, - "first_commit": "2024-07-26 09:05:34", - "latest_commit": "2024-07-27 05:59:10", + "score": 0.005406839390193189, + "first_commit": "2024-03-04 08:46:03", + "latest_commit": "2024-07-06 15:18:14", "languages": [], "model_or_dataset": "model", - "model_size": 70.6, - "model_architectures": null + "model_size": 6.83, + "model_architectures": "LlamaForCausalLM" }, { "description": "lists of text corpus and more (mainly Japanese)", @@ -2357,33 +2301,19 @@ "project_name": "dataset-list", "stargazers_count": 116, "source": "GitHub", - "score": 0.002720777554175735, + "score": 0.004925488992257032, "first_commit": "2015-11-21 22:38:56", "latest_commit": "2024-07-26 00:40:50", "languages": [], "model_or_dataset": null }, - { - "description": "日本語T5事前学習済みモデル This is a T5 (Text-to-Text Transfer Transformer) model pretrained on Japanese corpus. ", - "url": "https://huggingface.co/sonoisa/t5-base-japanese", - "project_name": "t5-base-japanese", - "downloads": 7388, - "source": "Hugging Face", - "score": 0.0016296057816761313, - "first_commit": "2021-03-28 10:54:32", - "latest_commit": "2022-07-31 08:20:41", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "T5Model" - }, { "description": "A comparison tool of Japanese tokenizers", "url": "https://github.com/taishi-i/toiro", "project_name": "toiro", "stargazers_count": 115, "source": "GitHub", - "score": -0.00021076445842205195, + "score": 0.001985468430987329, "first_commit": "2020-08-13 19:49:15", "latest_commit": "2023-07-31 23:55:55", "languages": [ @@ -2398,7 +2328,7 @@ "project_name": "ja_text_bert", "stargazers_count": 115, "source": "GitHub", - "score": -0.00021076445842205195, + "score": 0.001985468430987329, "first_commit": "2018-10-31 18:23:04", "latest_commit": "2018-11-08 15:17:20", "languages": [ @@ -2413,7 +2343,7 @@ "project_name": "GPTSAN", "stargazers_count": 115, "source": "GitHub", - "score": -0.00021076445842205195, + "score": 0.001985468430987329, "first_commit": "2022-02-11 14:38:55", "latest_commit": "2023-09-13 12:20:29", "languages": [ @@ -2422,32 +2352,60 @@ "model_or_dataset": "model" }, { - "description": "Swallow-MX-8x7b-NVE-v0.1 Our Swallow-MX-8x7b-NVE-v0.1 model has undergone continuous pre-training from the Mixtral-8x7B-Instruct-v0.1, primarily with the addition of Japanese language data.", - "url": "https://huggingface.co/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1", - "project_name": "Swallow-MX-8x7b-NVE-v0.1", - "downloads": 7257, + "description": "reazonspeech-nemo-v2 reazonspeech-nemo-v2 is an automatic speech recognition model trained on ReazonSpeech v2.0 corpus.", + "url": "https://huggingface.co/reazon-research/reazonspeech-nemo-v2", + "project_name": "reazonspeech-nemo-v2", + "downloads": 8921, "source": "Hugging Face", - "score": -0.0004285819452663081, - "first_commit": "2024-02-22 04:44:42", - "latest_commit": "2024-05-03 18:51:12", + "score": 0.0018117611583760118, + "first_commit": "2024-01-30 01:49:12", + "latest_commit": "2024-02-14 01:32:45", "languages": [], "model_or_dataset": "model", - "model_size": 46.7, - "model_architectures": "MixtralForCausalLM" + "model_size": null, + "model_architectures": null }, { - "description": "japanese-sentiment-analysis This model was trained from scratch on the chABSA dataset.", - "url": "https://huggingface.co/jarvisx17/japanese-sentiment-analysis", - "project_name": "japanese-sentiment-analysis", - "downloads": 6778, + "description": "BERT large Japanese (unidic-lite with whole word masking, jawiki-20200831)", + "url": "https://huggingface.co/tohoku-nlp/bert-large-japanese", + "project_name": "bert-large-japanese", + "downloads": 8602, "source": "Hugging Face", - "score": -0.007954321801796296, - "first_commit": "2022-11-15 06:28:39", - "latest_commit": "2024-01-20 14:45:14", + "score": -0.0015712180627144882, + "first_commit": "2021-03-05 06:17:13", + "latest_commit": "2021-09-23 15:45:41", "languages": [], "model_or_dataset": "model", - "model_size": 0.111, - "model_architectures": "BertForSequenceClassification" + "model_size": null, + "model_architectures": "BertForMaskedLM" + }, + { + "description": "luke-japanese-large luke-japanese is the Japanese version of LUKE (Language Understanding with Knowledge-based Embeddings), a pre-trained knowledge-enhanced contextualized representation of words and entities.", + "url": "https://huggingface.co/studio-ousia/luke-japanese-large", + "project_name": "luke-japanese-large", + "downloads": 8361, + "source": "Hugging Face", + "score": -0.004127011141970947, + "first_commit": "2022-11-07 14:25:53", + "latest_commit": "2022-11-09 11:18:56", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "LukeForMaskedLM" + }, + { + "description": "日本語T5事前学習済みモデル This is a T5 (Text-to-Text Transfer Transformer) model pretrained on Japanese corpus. ", + "url": "https://huggingface.co/sonoisa/t5-base-japanese", + "project_name": "t5-base-japanese", + "downloads": 8230, + "source": "Hugging Face", + "score": -0.0055162596622306825, + "first_commit": "2021-03-28 10:54:32", + "latest_commit": "2022-07-31 08:20:41", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "T5Model" }, { "description": "複数の前処理を構成して管理するテキスト前処理ツール", @@ -2455,7 +2413,7 @@ "project_name": "HojiChar", "stargazers_count": 112, "source": "GitHub", - "score": -0.009005390496215413, + "score": -0.006834593252821781, "first_commit": "2023-01-31 20:37:40", "latest_commit": "2024-08-15 17:25:48", "languages": [ @@ -2469,7 +2427,7 @@ "project_name": "pymlask", "stargazers_count": 112, "source": "GitHub", - "score": -0.009005390496215413, + "score": -0.006834593252821781, "first_commit": "2017-02-10 21:33:23", "latest_commit": "2024-07-26 01:27:14", "languages": [ @@ -2478,26 +2436,40 @@ "model_or_dataset": null }, { - "description": "ELYZA-japanese-Llama-2-7b-fast-instruct-gguf ELYZAさんが公開しているELYZA-japanese-Llama-2-7b-fast-instructのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-7b-fast-instruct-gguf", - "project_name": "ELYZA-japanese-Llama-2-7b-fast-instruct-gguf", - "downloads": 6682, + "description": "Fugaku-LLM-13B-instruct-gguf Fugaku-LLMさんが公開しているFugaku-LLM-13B-instructのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Fugaku-LLM-13B-instruct-gguf", + "project_name": "Fugaku-LLM-13B-instruct-gguf", + "downloads": 7807, "source": "Hugging Face", - "score": -0.009462612044441137, - "first_commit": "2023-08-29 15:31:01", - "latest_commit": "2023-11-16 14:27:48", + "score": -0.010002153739099904, + "first_commit": "2024-05-10 16:43:49", + "latest_commit": "2024-05-12 06:06:51", "languages": [], "model_or_dataset": "model", - "model_size": 6.85, + "model_size": 13.4, + "model_architectures": null + }, + { + "description": "Model Card for Japanese DeBERTa V3 base Model description This is a Japanese DeBERTa V3 base model pre-trained on LLM-jp corpus v1.0.", + "url": "https://huggingface.co/ku-nlp/deberta-v3-base-japanese", + "project_name": "deberta-v3-base-japanese", + "downloads": 7707, + "source": "Hugging Face", + "score": -0.011062648792733288, + "first_commit": "2024-04-23 05:08:21", + "latest_commit": "2024-04-28 06:08:55", + "languages": [], + "model_or_dataset": "model", + "model_size": null, "model_architectures": null }, { "description": "Tanuki-8B-dpo-v1.0 モデルについて Tanuki-8Bは、フルスクラッチで約1.3Tトークン事前学習を行った約8Bパラメータの大規模言語モデルです。", "url": "https://huggingface.co/weblab-GENIAC/Tanuki-8B-dpo-v1.0", "project_name": "Tanuki-8B-dpo-v1.0", - "downloads": 6304, + "downloads": 7643, "source": "Hugging Face", - "score": -0.015401504874855199, + "score": -0.011741365627058655, "first_commit": "2024-08-12 12:47:52", "latest_commit": "2024-09-02 23:47:02", "languages": [], @@ -2505,13 +2477,41 @@ "model_size": 7.51, "model_architectures": "LlamaForCausalLM" }, + { + "description": "Swallow-MX-8x7b-NVE-v0.1 Our Swallow-MX-8x7b-NVE-v0.1 model has undergone continuous pre-training from the Mixtral-8x7B-Instruct-v0.1, primarily with the addition of Japanese language data.", + "url": "https://huggingface.co/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1", + "project_name": "Swallow-MX-8x7b-NVE-v0.1", + "downloads": 7440, + "source": "Hugging Face", + "score": -0.013894170585934429, + "first_commit": "2024-02-22 04:44:42", + "latest_commit": "2024-05-03 18:51:12", + "languages": [], + "model_or_dataset": "model", + "model_size": 46.7, + "model_architectures": "MixtralForCausalLM" + }, + { + "description": "CyberAgentLM2-7B (CALM2-7B)", + "url": "https://huggingface.co/cyberagent/calm2-7b", + "project_name": "calm2-7b", + "downloads": 7424, + "source": "Hugging Face", + "score": -0.01406384979451577, + "first_commit": "2023-11-01 07:24:59", + "latest_commit": "2023-11-02 05:46:18", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "LlamaForCausalLM" + }, { "description": "A fast LSTM Language Model for large vocabulary language like Japanese and Chinese", "url": "https://github.com/jiali-ms/JLM", "project_name": "JLM", "stargazers_count": 109, "source": "GitHub", - "score": -0.017800016534008773, + "score": -0.01565465493663089, "first_commit": "2018-01-10 14:12:41", "latest_commit": "2019-06-04 21:35:33", "languages": [ @@ -2525,7 +2525,7 @@ "project_name": "t5-japanese", "stargazers_count": 109, "source": "GitHub", - "score": -0.017800016534008773, + "score": -0.01565465493663089, "first_commit": "2021-03-28 22:12:19", "latest_commit": "2023-07-20 21:36:10", "languages": [ @@ -2539,7 +2539,7 @@ "project_name": "tdmelodic", "stargazers_count": 109, "source": "GitHub", - "score": -0.017800016534008773, + "score": -0.01565465493663089, "first_commit": "2020-09-14 18:12:46", "latest_commit": "2024-03-22 01:44:10", "languages": [ @@ -2547,55 +2547,13 @@ ], "model_or_dataset": "dataset" }, - { - "description": "BERT large Japanese (unidic-lite with whole word masking, CC-100 and jawiki-20230102)", - "url": "https://huggingface.co/tohoku-nlp/bert-large-japanese-v2", - "project_name": "bert-large-japanese-v2", - "downloads": 6099, - "source": "Hugging Face", - "score": -0.018622332997169703, - "first_commit": "2023-05-19 00:40:35", - "latest_commit": "2023-05-19 00:47:40", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForPreTraining" - }, - { - "description": "Model Card for Japanese character-level DeBERTa V2 large Model description This is a Japanese DeBERTa V2 large model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.", - "url": "https://huggingface.co/ku-nlp/deberta-v2-large-japanese-char-wwm", - "project_name": "deberta-v2-large-japanese-char-wwm", - "downloads": 6006, - "source": "Hugging Face", - "score": -0.02008348916973189, - "first_commit": "2023-03-09 10:13:05", - "latest_commit": "2023-09-15 03:48:28", - "languages": [], - "model_or_dataset": "model", - "model_size": 0.33, - "model_architectures": "DebertaV2ForMaskedLM" - }, - { - "description": "japanese-roberta-base This repository provides a base-sized Japanese RoBERTa model.", - "url": "https://huggingface.co/rinna/japanese-roberta-base", - "project_name": "japanese-roberta-base", - "downloads": 5991, - "source": "Hugging Face", - "score": -0.02031915952014515, - "first_commit": "2021-06-11 02:56:39", - "latest_commit": "2024-07-20 07:44:40", - "languages": [], - "model_or_dataset": "model", - "model_size": 0.111, - "model_architectures": "RobertaForMaskedLM" - }, { "description": "Yet Another Japanese Dependency Structure Analyzer", "url": "https://github.com/taku910/cabocha", "project_name": "cabocha", "stargazers_count": 108, "source": "GitHub", - "score": -0.020731558546606563, + "score": -0.018594675497900594, "first_commit": "2011-07-29 04:08:14", "latest_commit": "2020-07-24 11:31:47", "languages": [ @@ -2614,7 +2572,7 @@ "project_name": "ja.text8", "stargazers_count": 108, "source": "GitHub", - "score": -0.020731558546606563, + "score": -0.018594675497900594, "first_commit": "2017-10-04 13:15:25", "latest_commit": "2017-10-04 13:38:23", "languages": [ @@ -2623,32 +2581,32 @@ "model_or_dataset": "dataset" }, { - "description": "【告知】chilled_remix及びreversemixは2023年5月21日にVersion変更を行い、v2へ移行いたしました。", - "url": "https://huggingface.co/sazyou-roukaku/chilled_remix", - "project_name": "chilled_remix", - "downloads": 5948, + "description": "Model Card for Japanese character-level DeBERTa V2 large Model description This is a Japanese DeBERTa V2 large model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.", + "url": "https://huggingface.co/ku-nlp/deberta-v2-large-japanese-char-wwm", + "project_name": "deberta-v2-large-japanese-char-wwm", + "downloads": 6760, "source": "Hugging Face", - "score": -0.020994747857996484, - "first_commit": "2023-04-18 12:48:48", - "latest_commit": "2023-06-09 23:08:31", + "score": -0.021105536950641452, + "first_commit": "2023-03-09 10:13:05", + "latest_commit": "2023-09-15 03:48:28", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": null + "model_size": 0.33, + "model_architectures": "DebertaV2ForMaskedLM" }, { - "description": "transformers-ud-japanese-electra-ginza-510 (sudachitra-wordpiece, mC4 Japanese)", - "url": "https://huggingface.co/megagonlabs/transformers-ud-japanese-electra-base-ginza-510", - "project_name": "transformers-ud-japanese-electra-base-ginza-510", - "downloads": 5838, + "description": "japanese-sentiment-analysis This model was trained from scratch on the chABSA dataset.", + "url": "https://huggingface.co/jarvisx17/japanese-sentiment-analysis", + "project_name": "japanese-sentiment-analysis", + "downloads": 6563, "source": "Hugging Face", - "score": -0.022722997094360365, - "first_commit": "2021-12-05 11:31:57", - "latest_commit": "2021-12-05 21:12:12", + "score": -0.02319471220629922, + "first_commit": "2022-11-15 06:28:39", + "latest_commit": "2024-01-20 14:45:14", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "ElectraModel" + "model_size": 0.111, + "model_architectures": "BertForSequenceClassification" }, { "description": "JaQuAD: Japanese Question Answering Dataset for Machine Reading Comprehension (2022, Skelter Labs)", @@ -2656,7 +2614,7 @@ "project_name": "JaQuAD", "stargazers_count": 106, "source": "GitHub", - "score": -0.026594642571802135, + "score": -0.024474716620440002, "first_commit": "2022-01-11 16:58:07", "latest_commit": "2022-02-04 11:42:51", "languages": [ @@ -2664,13 +2622,27 @@ ], "model_or_dataset": "dataset" }, + { + "description": "BERT large Japanese (unidic-lite with whole word masking, CC-100 and jawiki-20230102)", + "url": "https://huggingface.co/tohoku-nlp/bert-large-japanese-v2", + "project_name": "bert-large-japanese-v2", + "downloads": 6186, + "source": "Hugging Face", + "score": -0.027192778558497083, + "first_commit": "2023-05-19 00:40:35", + "latest_commit": "2023-05-19 00:47:40", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "BertForPreTraining" + }, { "description": "Yet another mecab wrapper for nodejs", "url": "https://github.com/golbin/node-mecab-ya", "project_name": "node-mecab-ya", "stargazers_count": 105, "source": "GitHub", - "score": -0.02952618458439992, + "score": -0.027414737181709704, "first_commit": "2016-04-09 23:34:34", "latest_commit": "2021-06-18 18:30:43", "languages": [ @@ -2679,32 +2651,60 @@ "model_or_dataset": null }, { - "description": "ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF Original Model elyza/ELYZA-japanese-Llama-2-13b-fast-instruct Run with LlamaEdge LlamaEdge version: v0.2.8 and above Prompt template Prompt type: llama-2-chat Prompt string <s>[INST] <<SYS>> {{ system_prompt }} <</SYS>> {{ user_msg_1 }}", - "url": "https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF", - "project_name": "ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF", - "downloads": 5032, + "description": "japanese-roberta-base This repository provides a base-sized Japanese RoBERTa model.", + "url": "https://huggingface.co/rinna/japanese-roberta-base", + "project_name": "japanese-roberta-base", + "downloads": 5861, "source": "Hugging Face", - "score": -0.03538635058989934, - "first_commit": "2024-01-06 03:33:53", - "latest_commit": "2024-03-20 07:21:25", + "score": -0.030639387482805588, + "first_commit": "2021-06-11 02:56:39", + "latest_commit": "2024-07-20 07:44:40", "languages": [], "model_or_dataset": "model", - "model_size": 13.1, - "model_architectures": "LlamaForCausalLM" + "model_size": 0.111, + "model_architectures": "RobertaForMaskedLM" }, { - "description": "japanese-gpt2-medium This repository provides a medium-sized Japanese GPT-2 model.", - "url": "https://huggingface.co/rinna/japanese-gpt2-medium", - "project_name": "japanese-gpt2-medium", - "downloads": 4942, + "description": "transformers-ud-japanese-electra-ginza-510 (sudachitra-wordpiece, mC4 Japanese)", + "url": "https://huggingface.co/megagonlabs/transformers-ud-japanese-electra-base-ginza-510", + "project_name": "transformers-ud-japanese-electra-base-ginza-510", + "downloads": 5810, "source": "Hugging Face", - "score": -0.03680037269237888, - "first_commit": "2021-04-05 02:01:26", - "latest_commit": "2024-07-20 07:50:47", + "score": -0.031180239960158614, + "first_commit": "2021-12-05 11:31:57", + "latest_commit": "2021-12-05 21:12:12", "languages": [], "model_or_dataset": "model", - "model_size": 0.361, - "model_architectures": "GPT2LMHeadModel" + "model_size": null, + "model_architectures": "ElectraModel" + }, + { + "description": "【告知】chilled_remix及びreversemixは2023年5月21日にVersion変更を行い、v2へ移行いたしました。", + "url": "https://huggingface.co/sazyou-roukaku/chilled_remix", + "project_name": "chilled_remix", + "downloads": 5470, + "source": "Hugging Face", + "score": -0.034785923142512123, + "first_commit": "2023-04-18 12:48:48", + "latest_commit": "2023-06-09 23:08:31", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": null + }, + { + "description": "OpenCALM-7B Model Description OpenCALM is a suite of decoder-only language models pre-trained on Japanese datasets, developed by", + "url": "https://huggingface.co/cyberagent/open-calm-7b", + "project_name": "open-calm-7b", + "downloads": 5355, + "source": "Hugging Face", + "score": -0.03600549245419052, + "first_commit": "2023-05-15 07:53:34", + "latest_commit": "2023-05-18 01:12:08", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "GPTNeoXForCausalLM" }, { "description": "An example usage of JParaCrawl pre-trained Neural Machine Translation (NMT) models.", @@ -2712,7 +2712,7 @@ "project_name": "jparacrawl-finetune", "stargazers_count": 102, "source": "GitHub", - "score": -0.03832081062219329, + "score": -0.036234798865518815, "first_commit": "2019-11-17 14:46:58", "latest_commit": "2021-04-29 14:27:00", "languages": [ @@ -2726,7 +2726,7 @@ "project_name": "Kamite", "stargazers_count": 102, "source": "GitHub", - "score": -0.03832081062219329, + "score": -0.036234798865518815, "first_commit": "2022-07-08 19:26:15", "latest_commit": "2024-02-22 23:41:52", "languages": [ @@ -2745,7 +2745,7 @@ "project_name": "house-of-councillors", "stargazers_count": 102, "source": "GitHub", - "score": -0.03832081062219329, + "score": -0.036234798865518815, "first_commit": "2022-06-16 16:06:39", "latest_commit": "2024-08-15 14:22:06", "languages": [ @@ -2755,89 +2755,33 @@ "model_or_dataset": "dataset" }, { - "description": "reazonspeech-nemo-v2 reazonspeech-nemo-v2 is an automatic speech recognition model trained on ReazonSpeech v2.0 corpus.", - "url": "https://huggingface.co/reazon-research/reazonspeech-nemo-v2", - "project_name": "reazonspeech-nemo-v2", - "downloads": 4818, + "description": "japanese-gpt2-medium This repository provides a medium-sized Japanese GPT-2 model.", + "url": "https://huggingface.co/rinna/japanese-gpt2-medium", + "project_name": "japanese-gpt2-medium", + "downloads": 5237, "source": "Hugging Face", - "score": -0.0387485809224618, - "first_commit": "2024-01-30 01:49:12", - "latest_commit": "2024-02-14 01:32:45", + "score": -0.03725687661747791, + "first_commit": "2021-04-05 02:01:26", + "latest_commit": "2024-07-20 07:50:47", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": null + "model_size": 0.361, + "model_architectures": "GPT2LMHeadModel" }, { - "description": "OpenCALM-7B Model Description OpenCALM is a suite of decoder-only language models pre-trained on Japanese datasets, developed by", - "url": "https://huggingface.co/cyberagent/open-calm-7b", - "project_name": "open-calm-7b", - "downloads": 4766, - "source": "Hugging Face", - "score": -0.03956557147056109, - "first_commit": "2023-05-15 07:53:34", - "latest_commit": "2023-05-18 01:12:08", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "GPTNeoXForCausalLM" - }, - { - "description": "自動生成のマルチターンデータセット オープンなデータソースから､Calm3-22bを使ってQ&Aを自動生成したものです｡ 一部の計算には東京工業大学のスーパーコンピュータTSUBAME4.0を利用しました｡ データソース はじめの質問(q1)を､種々のデータソースから収集しました｡その後のやりとりはすべて､Calmが生成しました｡質問文については､元データのライセンスに準拠します｡ oasst2-33k-ja apache 2.0 databricks-dolly-15k-ja cc-by-sa-3.0 minnade CC0 cyberagent/chatbot-arena-ja-calm2-7b-chat-experimental cc-by-4.0", - "url": "https://huggingface.co/datasets/kanhatakeyama/AutoMultiTurnByCalm3-22B", - "project_name": "AutoMultiTurnByCalm3-22B", - "downloads": 4734, - "source": "Hugging Face", - "score": -0.040068334884776034, - "first_commit": "2024-07-17 09:53:20", - "latest_commit": "2024-07-17 10:03:02", - "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null - }, - { - "description": "DeBERTa V2 small Japanese This is a DeBERTaV2 model pretrained on Japanese texts.", - "url": "https://huggingface.co/izumi-lab/deberta-v2-small-japanese", - "project_name": "deberta-v2-small-japanese", - "downloads": 4703, - "source": "Hugging Face", - "score": -0.04055538694229677, - "first_commit": "2023-10-21 13:24:28", - "latest_commit": "2024-07-19 03:08:14", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "DebertaV2ForMaskedLM" - }, - { - "description": "japanese-gpt-neox-3.6b Overview This repository provides a Japanese GPT-NeoX model of 3.6 billion parameters.", - "url": "https://huggingface.co/rinna/japanese-gpt-neox-3.6b", - "project_name": "japanese-gpt-neox-3.6b", - "downloads": 4681, - "source": "Hugging Face", - "score": -0.04090103678956954, - "first_commit": "2023-05-17 02:16:45", - "latest_commit": "2024-07-20 07:55:19", - "languages": [], - "model_or_dataset": "model", - "model_size": 3.76, - "model_architectures": "GPTNeoXForCausalLM" - }, - { - "description": "CJK computer science terms comparison / 中日韓電腦科學術語對照 / 日中韓のコンピュータ科学の用語対照 / 한·중·일 전산학 용어 대조", - "url": "https://github.com/dahlia/cjk-compsci-terms", - "project_name": "cjk-compsci-terms", - "stargazers_count": 101, - "source": "GitHub", - "score": -0.04125235263479107, - "first_commit": "2020-12-19 06:11:14", - "latest_commit": "2022-09-16 01:27:59", - "languages": [ - "Python", - "JavaScript" - ], - "model_or_dataset": "dataset" + "description": "CJK computer science terms comparison / 中日韓電腦科學術語對照 / 日中韓のコンピュータ科学の用語対照 / 한·중·일 전산학 용어 대조", + "url": "https://github.com/dahlia/cjk-compsci-terms", + "project_name": "cjk-compsci-terms", + "stargazers_count": 101, + "source": "GitHub", + "score": -0.03917481942678852, + "first_commit": "2020-12-19 06:11:14", + "latest_commit": "2022-09-16 01:27:59", + "languages": [ + "Python", + "JavaScript" + ], + "model_or_dataset": "dataset" }, { "description": "Japanese Word Similarity Dataset", @@ -2845,7 +2789,7 @@ "project_name": "JapaneseWordSimilarityDataset", "stargazers_count": 101, "source": "GitHub", - "score": -0.04125235263479107, + "score": -0.03917481942678852, "first_commit": "2016-01-08 16:25:16", "latest_commit": "2021-12-07 12:22:07", "languages": [ @@ -2859,7 +2803,7 @@ "project_name": "japanese-pitch-accent-resources", "stargazers_count": 101, "source": "GitHub", - "score": -0.04125235263479107, + "score": -0.03917481942678852, "first_commit": "2018-03-03 15:51:09", "latest_commit": "2024-02-11 00:55:27", "languages": [], @@ -2869,9 +2813,9 @@ "description": "bert-large-japanese-upos Model Description", "url": "https://huggingface.co/KoichiYasuoka/bert-large-japanese-upos", "project_name": "bert-large-japanese-upos", - "downloads": 4651, + "downloads": 4786, "source": "Hugging Face", - "score": -0.04137237749039605, + "score": -0.04203970930936448, "first_commit": "2021-08-19 10:39:38", "latest_commit": "2022-09-18 19:43:53", "languages": [], @@ -2880,40 +2824,68 @@ "model_architectures": "BertForTokenClassification" }, { - "description": "Llama-3-ELYZA-JP-8B-GGUF Model Description Llama-3-ELYZA-JP-8B is a large language model trained by ELYZA, Inc.", - "url": "https://huggingface.co/elyza/Llama-3-ELYZA-JP-8B-GGUF", - "project_name": "Llama-3-ELYZA-JP-8B-GGUF", - "downloads": 4549, + "description": "DeBERTa V2 small Japanese This is a DeBERTaV2 model pretrained on Japanese texts.", + "url": "https://huggingface.co/izumi-lab/deberta-v2-small-japanese", + "project_name": "deberta-v2-small-japanese", + "downloads": 4729, "source": "Hugging Face", - "score": -0.0429749358732062, - "first_commit": "2024-06-25 07:29:22", - "latest_commit": "2024-06-26 02:56:52", + "score": -0.042644191489935514, + "first_commit": "2023-10-21 13:24:28", + "latest_commit": "2024-07-19 03:08:14", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": null + "model_size": null, + "model_architectures": "DebertaV2ForMaskedLM" }, { - "description": "Llama-3-8B-Japanese-Instruct-GGUF Original Model haqishen/Llama-3-8B-Japanese-Instruct Run with LlamaEdge LlamaEdge version: v0.10.1 and above Prompt template Prompt type: llama-3-chat Prompt string <|begin_of_text|><|start_header_id|>system<|end_header_id|> {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|> {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|> {{ model_answer_1 }}<|eot_id|><|start_header", - "url": "https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF", - "project_name": "Llama-3-8B-Japanese-Instruct-GGUF", - "downloads": 4398, + "description": "Llama-3.1-70B-Japanese-Instruct-2407-gguf cyberagentさんが公開しているLlama-3.1-70B-Japanese-Instruct-2407のggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Llama-3.1-70B-Japanese-Instruct-2407-gguf", + "project_name": "Llama-3.1-70B-Japanese-Instruct-2407-gguf", + "downloads": 4668, "source": "Hugging Face", - "score": -0.04534735073403298, - "first_commit": "2024-05-14 05:37:53", - "latest_commit": "2024-05-14 06:42:38", + "score": -0.04329109347265188, + "first_commit": "2024-07-26 09:05:34", + "latest_commit": "2024-07-27 05:59:10", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, + "model_size": 70.6, "model_architectures": null }, + { + "description": "ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF Original Model elyza/ELYZA-japanese-Llama-2-13b-fast-instruct Run with LlamaEdge LlamaEdge version: v0.2.8 and above Prompt template Prompt type: llama-2-chat Prompt string <s>[INST] <<SYS>> {{ system_prompt }} <</SYS>> {{ user_msg_1 }}", + "url": "https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF", + "project_name": "ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF", + "downloads": 4594, + "source": "Hugging Face", + "score": -0.04407585981234058, + "first_commit": "2024-01-06 03:33:53", + "latest_commit": "2024-03-20 07:21:25", + "languages": [], + "model_or_dataset": "model", + "model_size": 13.1, + "model_architectures": "LlamaForCausalLM" + }, + { + "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", + "url": "https://huggingface.co/tokyotech-llm/Swallow-13b-instruct-hf", + "project_name": "Swallow-13b-instruct-hf", + "downloads": 4403, + "source": "Hugging Face", + "score": -0.04610140536478035, + "first_commit": "2023-12-07 03:10:55", + "latest_commit": "2024-06-29 08:56:29", + "languages": [], + "model_or_dataset": "model", + "model_size": 13.1, + "model_architectures": "LlamaForCausalLM" + }, { "description": "ELYZA-japanese-Llama-2-7b Model Description ELYZA-japanese-Llama-2-7b は、 Llama2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。 ", "url": "https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b", "project_name": "ELYZA-japanese-Llama-2-7b", - "downloads": 4302, + "downloads": 4303, "source": "Hugging Face", - "score": -0.04685564097667782, + "score": -0.047161900418413734, "first_commit": "2023-08-28 12:38:34", "latest_commit": "2023-08-29 03:45:51", "languages": [], @@ -2922,18 +2894,18 @@ "model_architectures": "LlamaForCausalLM" }, { - "description": "RetrievaBERT Model The RetrievaBERT is the pre-trained Transformer Encoder using Megatron-LM.", - "url": "https://huggingface.co/retrieva-jp/bert-1.3b", - "project_name": "bert-1.3b", - "downloads": 4137, + "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", + "url": "https://huggingface.co/tokyotech-llm/Swallow-7b-hf", + "project_name": "Swallow-7b-hf", + "downloads": 4298, "source": "Hugging Face", - "score": -0.04944801483122364, - "first_commit": "2024-06-25 06:18:24", - "latest_commit": "2024-07-09 05:36:08", + "score": -0.04721492517109541, + "first_commit": "2023-11-25 10:09:49", + "latest_commit": "2024-06-29 08:56:17", "languages": [], "model_or_dataset": "model", - "model_size": 1.3, - "model_architectures": "RetrievaBertForMaskedLM" + "model_size": 6.83, + "model_architectures": "LlamaForCausalLM" }, { "description": "Asynchronous japanese morphological analyser using MeCab.", @@ -2941,7 +2913,7 @@ "project_name": "node-mecab-async", "stargazers_count": 98, "source": "GitHub", - "score": -0.05004697867258443, + "score": -0.04799488111059763, "first_commit": "2012-10-29 09:32:49", "latest_commit": "2017-10-29 14:56:11", "languages": [ @@ -2955,7 +2927,7 @@ "project_name": "jiten", "stargazers_count": 98, "source": "GitHub", - "score": -0.05004697867258443, + "score": -0.04799488111059763, "first_commit": "2020-06-15 02:09:21", "latest_commit": "2023-12-16 23:43:06", "languages": [ @@ -2965,13 +2937,27 @@ ], "model_or_dataset": "dataset" }, + { + "description": "ELYZA-japanese-Llama-2-13b Model Description ELYZA-japanese-Llama-2-13b は、 Llama 2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。", + "url": "https://huggingface.co/elyza/ELYZA-japanese-Llama-2-13b-instruct", + "project_name": "ELYZA-japanese-Llama-2-13b-instruct", + "downloads": 4186, + "source": "Hugging Face", + "score": -0.0484026796311648, + "first_commit": "2023-12-25 16:10:32", + "latest_commit": "2023-12-27 01:41:15", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "LlamaForCausalLM" + }, { "description": "Llama 3 Youko 8B (rinna/llama-3-youko-8b)", "url": "https://huggingface.co/rinna/llama-3-youko-8b", "project_name": "llama-3-youko-8b", - "downloads": 4045, + "downloads": 4173, "source": "Hugging Face", - "score": -0.05089345964709161, + "score": -0.04854054398813713, "first_commit": "2024-05-01 07:53:46", "latest_commit": "2024-07-25 05:14:42", "languages": [], @@ -2980,68 +2966,124 @@ "model_architectures": "LlamaForCausalLM" }, { - "description": "ELYZA-japanese-Llama-2-13b Model Description ELYZA-japanese-Llama-2-13b は、 Llama 2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。", - "url": "https://huggingface.co/elyza/ELYZA-japanese-Llama-2-13b-instruct", - "project_name": "ELYZA-japanese-Llama-2-13b-instruct", - "downloads": 4019, + "description": "RetrievaBERT Model The RetrievaBERT is the pre-trained Transformer Encoder using Megatron-LM.", + "url": "https://huggingface.co/retrieva-jp/bert-1.3b", + "project_name": "bert-1.3b", + "downloads": 4112, "source": "Hugging Face", - "score": -0.05130195492114126, - "first_commit": "2023-12-25 16:10:32", - "latest_commit": "2023-12-27 01:41:15", + "score": -0.0491874459708535, + "first_commit": "2024-06-25 06:18:24", + "latest_commit": "2024-07-09 05:36:08", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LlamaForCausalLM" + "model_size": 1.3, + "model_architectures": "RetrievaBertForMaskedLM" }, { - "description": "This is a dataset collection of JMedBench, which is a benchmark for evaluating Japanese biomedical large language models (LLMs).", - "url": "https://huggingface.co/datasets/Coldog2333/JMedBench", - "project_name": "JMedBench", - "downloads": 4006, + "description": "japanese-gpt-neox-3.6b Overview This repository provides a Japanese GPT-NeoX model of 3.6 billion parameters.", + "url": "https://huggingface.co/rinna/japanese-gpt-neox-3.6b", + "project_name": "japanese-gpt-neox-3.6b", + "downloads": 4080, "source": "Hugging Face", - "score": -0.05150620255816608, - "first_commit": "2024-08-17 11:12:54", - "latest_commit": "2024-09-01 12:41:40", + "score": -0.04952680438801618, + "first_commit": "2023-05-17 02:16:45", + "latest_commit": "2024-07-20 07:55:19", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_or_dataset": "model", + "model_size": 3.76, + "model_architectures": "GPTNeoXForCausalLM" + }, + { + "description": "Llama-3-ELYZA-JP-8B-GGUF Model Description Llama-3-ELYZA-JP-8B is a large language model trained by ELYZA, Inc.", + "url": "https://huggingface.co/elyza/Llama-3-ELYZA-JP-8B-GGUF", + "project_name": "Llama-3-ELYZA-JP-8B-GGUF", + "downloads": 3987, + "source": "Hugging Face", + "score": -0.05051306478789523, + "first_commit": "2024-06-25 07:29:22", + "latest_commit": "2024-06-26 02:56:52", + "languages": [], + "model_or_dataset": "model", + "model_size": 8.03, "model_architectures": null }, { - "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", - "url": "https://huggingface.co/tokyotech-llm/Swallow-13b-instruct-hf", - "project_name": "Swallow-13b-instruct-hf", - "downloads": 3681, + "description": "このモデルはLuke-japanese-large-liteをファインチューニングしたものです。 ", + "url": "https://huggingface.co/Mizuiro-sakura/luke-japanese-large-sentiment-analysis-wrime", + "project_name": "luke-japanese-large-sentiment-analysis-wrime", + "downloads": 3906, "source": "Hugging Face", - "score": -0.05661239348378663, - "first_commit": "2023-12-07 03:10:55", - "latest_commit": "2024-06-29 08:56:29", + "score": -0.05137206578133827, + "first_commit": "2023-03-13 12:40:08", + "latest_commit": "2023-05-15 12:58:08", "languages": [], "model_or_dataset": "model", - "model_size": 13.1, - "model_architectures": "LlamaForCausalLM" + "model_size": 0.41400000000000003, + "model_architectures": "LukeForSequenceClassification" }, { - "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", - "url": "https://huggingface.co/tokyotech-llm/Swallow-7b-hf", - "project_name": "Swallow-7b-hf", - "downloads": 3569, + "description": "japanese-gpt2-xsmall", + "url": "https://huggingface.co/rinna/japanese-gpt2-xsmall", + "project_name": "japanese-gpt2-xsmall", + "downloads": 3856, "source": "Hugging Face", - "score": -0.05837206543353895, - "first_commit": "2023-11-25 10:09:49", - "latest_commit": "2024-06-29 08:56:17", + "score": -0.051902313308154965, + "first_commit": "2021-07-26 02:52:54", + "latest_commit": "2024-07-20 07:48:11", "languages": [], "model_or_dataset": "model", - "model_size": 6.83, + "model_size": 0.0437, + "model_architectures": "GPT2LMHeadModel" + }, + { + "description": "rinna/youri-7b Overview We conduct continual pre-training of llama2-7b on 40B tokens from a mixture of Japanese and English datasets.", + "url": "https://huggingface.co/rinna/youri-7b", + "project_name": "youri-7b", + "downloads": 3837, + "source": "Hugging Face", + "score": -0.05210380736834531, + "first_commit": "2023-10-30 15:12:17", + "latest_commit": "2024-07-22 08:01:22", + "languages": [], + "model_or_dataset": "model", + "model_size": 6.74, "model_architectures": "LlamaForCausalLM" }, + { + "description": "Llama-3-8B-Japanese-Instruct-GGUF Original Model haqishen/Llama-3-8B-Japanese-Instruct Run with LlamaEdge LlamaEdge version: v0.10.1 and above Prompt template Prompt type: llama-3-chat Prompt string <|begin_of_text|><|start_header_id|>system<|end_header_id|> {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|> {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|> {{ model_answer_1 }}<|eot_id|><|start_header", + "url": "https://huggingface.co/second-state/Llama-3-8B-Japanese-Instruct-GGUF", + "project_name": "Llama-3-8B-Japanese-Instruct-GGUF", + "downloads": 3474, + "source": "Hugging Face", + "score": -0.0559534044130345, + "first_commit": "2024-05-14 05:37:53", + "latest_commit": "2024-05-14 06:42:38", + "languages": [], + "model_or_dataset": "model", + "model_size": 8.03, + "model_architectures": null + }, + { + "description": "OpenCALM-Small Model Description OpenCALM is a suite of decoder-only language models pre-trained on Japanese datasets, developed by", + "url": "https://huggingface.co/cyberagent/open-calm-small", + "project_name": "open-calm-small", + "downloads": 3330, + "source": "Hugging Face", + "score": -0.057480517290266576, + "first_commit": "2023-05-15 06:40:15", + "latest_commit": "2023-05-18 01:10:33", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "GPTNeoXForCausalLM" + }, { "description": "Kotoba-Whisper-v1.1 Kotoba-Whisper-v1.1 is a Japanese ASR model based on kotoba-tech/kotoba-whisper-v1.0, with additional postprocessing stacks integrated as pipeline.", "url": "https://huggingface.co/kotoba-tech/kotoba-whisper-v1.1", "project_name": "kotoba-whisper-v1.1", - "downloads": 3546, + "downloads": 3286, "source": "Hugging Face", - "score": -0.05873342663750594, + "score": -0.05794713511386527, "first_commit": "2024-04-29 14:53:48", "latest_commit": "2024-05-08 15:34:40", "languages": [], @@ -3049,13 +3091,27 @@ "model_size": 0.756, "model_architectures": "WhisperForConditionalGeneration" }, + { + "description": "sbert-jsnli-luke-japanese-base-lite This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.", + "url": "https://huggingface.co/oshizo/sbert-jsnli-luke-japanese-base-lite", + "project_name": "sbert-jsnli-luke-japanese-base-lite", + "downloads": 3275, + "source": "Hugging Face", + "score": -0.05806378956976494, + "first_commit": "2023-01-10 11:53:15", + "latest_commit": "2023-01-10 12:36:12", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "LukeModel" + }, { "description": "AIBunCho/japanese-novel-gpt-j-6b AI BunChoさんが公開しているjapanese-novel-gpt-j-6bのgguf変換版です。 ", "url": "https://huggingface.co/mmnga/aibuncho-japanese-novel-gpt-j-6b-gguf", "project_name": "aibuncho-japanese-novel-gpt-j-6b-gguf", - "downloads": 3388, + "downloads": 3243, "source": "Hugging Face", - "score": -0.061215820995192245, + "score": -0.05840314798692762, "first_commit": "2023-09-03 17:32:44", "latest_commit": "2023-09-11 01:10:36", "languages": [], @@ -3064,26 +3120,40 @@ "model_architectures": null }, { - "description": "rinna/youri-7b Overview We conduct continual pre-training of llama2-7b on 40B tokens from a mixture of Japanese and English datasets.", - "url": "https://huggingface.co/rinna/youri-7b", - "project_name": "youri-7b", - "downloads": 3359, + "description": "Model Card for Model ID 実験モデルです /", + "url": "https://huggingface.co/mmnga/Llama-3-70B-japanese-suzume-vector-v0.1", + "project_name": "Llama-3-70B-japanese-suzume-vector-v0.1", + "downloads": 3191, "source": "Hugging Face", - "score": -0.061671450339324536, - "first_commit": "2023-10-30 15:12:17", - "latest_commit": "2024-07-22 08:01:22", + "score": -0.05895460541481698, + "first_commit": "2024-04-28 04:11:49", + "latest_commit": "2024-04-28 07:46:32", "languages": [], "model_or_dataset": "model", - "model_size": 6.74, + "model_size": 70.6, "model_architectures": "LlamaForCausalLM" }, + { + "description": "Japanese Stable LM Instruct Gamma 7B Model Description", + "url": "https://huggingface.co/stabilityai/japanese-stablelm-instruct-gamma-7b", + "project_name": "japanese-stablelm-instruct-gamma-7b", + "downloads": 3134, + "source": "Hugging Face", + "score": -0.05955908759538801, + "first_commit": "2023-10-16 08:55:06", + "latest_commit": "2024-01-24 05:54:38", + "languages": [], + "model_or_dataset": "model", + "model_size": 7.24, + "model_architectures": "MistralForCausalLM" + }, { "description": "Japanese Company Lexicon (JCLdic)", "url": "https://github.com/chakki-works/Japanese-Company-Lexicon", "project_name": "Japanese-Company-Lexicon", "stargazers_count": 94, "source": "GitHub", - "score": -0.061773146722975576, + "score": -0.05975496335567644, "first_commit": "2020-01-16 15:25:09", "latest_commit": "2023-01-21 14:50:18", "languages": [ @@ -3097,7 +3167,7 @@ "project_name": "genshin-dict", "stargazers_count": 94, "source": "GitHub", - "score": -0.061773146722975576, + "score": -0.05975496335567644, "first_commit": "2021-05-05 00:02:08", "latest_commit": "2024-07-15 16:47:41", "languages": [ @@ -3106,40 +3176,82 @@ "model_or_dataset": "dataset" }, { - "description": "bert-base-japanese-upos Model Description", - "url": "https://huggingface.co/KoichiYasuoka/bert-base-japanese-upos", - "project_name": "bert-base-japanese-upos", - "downloads": 3201, + "description": "Llama3 Swallow", + "url": "https://huggingface.co/tokyotech-llm/Llama-3-Swallow-70B-Instruct-v0.1", + "project_name": "Llama-3-Swallow-70B-Instruct-v0.1", + "downloads": 3080, "source": "Hugging Face", - "score": -0.06415384469701084, - "first_commit": "2021-08-26 23:02:50", - "latest_commit": "2022-09-18 19:43:26", + "score": -0.06013175492435004, + "first_commit": "2024-06-28 16:17:32", + "latest_commit": "2024-07-19 08:08:59", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForTokenClassification" + "model_size": 70.6, + "model_architectures": "LlamaForCausalLM" }, { - "description": "OpenCALM-Small Model Description OpenCALM is a suite of decoder-only language models pre-trained on Japanese datasets, developed by", - "url": "https://huggingface.co/cyberagent/open-calm-small", - "project_name": "open-calm-small", - "downloads": 3178, + "description": "Japanese-StableLM-Base-Beta-7B A cute robot wearing a kimono writes calligraphy with one single brush — Stable Diffusion XL Model Description japanese-stablelm-base-beta-7b is a 7B-parameter decoder-only language model based on Llama-2-7b that has been fine-tuned on a diverse collection of Japanese data, with the intent of maximizing downstream performance on Japanese language tasks.", + "url": "https://huggingface.co/stabilityai/japanese-stablelm-base-beta-7b", + "project_name": "japanese-stablelm-base-beta-7b", + "downloads": 3064, "source": "Hugging Face", - "score": -0.06451520590097784, - "first_commit": "2023-05-15 06:40:15", - "latest_commit": "2023-05-18 01:10:33", + "score": -0.06030143413293138, + "first_commit": "2023-10-30 07:43:36", + "latest_commit": "2023-12-19 06:43:01", "languages": [], "model_or_dataset": "model", - "model_size": null, + "model_size": 6.74, + "model_architectures": "LlamaForCausalLM" + }, + { + "description": "japanese-gpt-neox-3.6b-instruction-ppo Overview This repository provides a Japanese GPT-NeoX model of 3.6 billion parameters.", + "url": "https://huggingface.co/rinna/japanese-gpt-neox-3.6b-instruction-ppo", + "project_name": "japanese-gpt-neox-3.6b-instruction-ppo", + "downloads": 3002, + "source": "Hugging Face", + "score": -0.06095894106618408, + "first_commit": "2023-05-30 01:50:48", + "latest_commit": "2024-07-20 07:58:49", + "languages": [], + "model_or_dataset": "model", + "model_size": 3.76, "model_architectures": "GPTNeoXForCausalLM" }, + { + "description": "stockmark/stockmark-13b Stockmark-13b is a 13 billion parameter LLM pretrained from scratch based on Japanese corpus of about 220B tokens.", + "url": "https://huggingface.co/stockmark/stockmark-13b", + "project_name": "stockmark-13b", + "downloads": 2863, + "source": "Hugging Face", + "score": -0.062433029190734485, + "first_commit": "2023-10-21 06:53:06", + "latest_commit": "2024-05-17 06:15:56", + "languages": [], + "model_or_dataset": "model", + "model_size": 13.2, + "model_architectures": "LlamaForCausalLM" + }, + { + "description": "Japanese SimCSE (BERT-base)", + "url": "https://huggingface.co/pkshatech/simcse-ja-bert-base-clcmlp", + "project_name": "simcse-ja-bert-base-clcmlp", + "downloads": 2850, + "source": "Hugging Face", + "score": -0.06257089354770683, + "first_commit": "2022-12-26 02:52:03", + "latest_commit": "2023-01-27 06:44:23", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "BertModel" + }, { "description": "Japanese Morphological Analyzer written in Rust", "url": "https://github.com/togatoga/kanpyo", "project_name": "kanpyo", "stargazers_count": 93, "source": "GitHub", - "score": -0.06470468873557336, + "score": -0.06269498391694614, "first_commit": "2023-10-12 08:02:23", "latest_commit": "2024-08-20 08:56:37", "languages": [ @@ -3148,73 +3260,73 @@ "model_or_dataset": null }, { - "description": "Model Card for Model ID 実験モデルです /", - "url": "https://huggingface.co/mmnga/Llama-3-70B-japanese-suzume-vector-v0.1", - "project_name": "Llama-3-70B-japanese-suzume-vector-v0.1", - "downloads": 3165, + "description": "Llama3 Swallow", + "url": "https://huggingface.co/tokyotech-llm/Llama-3-Swallow-70B-v0.1", + "project_name": "Llama-3-Swallow-70B-v0.1", + "downloads": 2729, "source": "Hugging Face", - "score": -0.06471945353800265, - "first_commit": "2024-04-28 04:11:49", - "latest_commit": "2024-04-28 07:46:32", + "score": -0.06385409256260323, + "first_commit": "2024-06-14 05:56:33", + "latest_commit": "2024-07-01 06:24:32", "languages": [], "model_or_dataset": "model", "model_size": 70.6, "model_architectures": "LlamaForCausalLM" }, { - "description": "Llama3 Swallow", - "url": "https://huggingface.co/tokyotech-llm/Llama-3-Swallow-70B-Instruct-v0.1", - "project_name": "Llama-3-Swallow-70B-Instruct-v0.1", - "downloads": 3062, + "description": "clip-japanese-base This is a Japanese CLIP (Contrastive Language-Image Pre-training) model developed by LY Corporation.", + "url": "https://huggingface.co/line-corporation/clip-japanese-base", + "project_name": "clip-japanese-base", + "downloads": 2728, "source": "Hugging Face", - "score": -0.06633772327750702, - "first_commit": "2024-06-28 16:17:32", - "latest_commit": "2024-07-19 08:08:59", + "score": -0.06386469751313956, + "first_commit": "2024-04-24 01:36:22", + "latest_commit": "2024-05-10 03:07:04", "languages": [], "model_or_dataset": "model", - "model_size": 70.6, - "model_architectures": "LlamaForCausalLM" + "model_size": 0.197, + "model_architectures": "CLYPModel" }, { - "description": "Japanese SimCSE (BERT-base)", - "url": "https://huggingface.co/pkshatech/simcse-ja-bert-base-clcmlp", - "project_name": "simcse-ja-bert-base-clcmlp", - "downloads": 3035, + "description": "Llama-3.1-70B-Japanese-Instruct-2407 Model Description This is a Japanese continually pre-trained model based on meta-llama/Meta-Llama-3.1-70B-Instruct.", + "url": "https://huggingface.co/cyberagent/Llama-3.1-70B-Japanese-Instruct-2407", + "project_name": "Llama-3.1-70B-Japanese-Instruct-2407", + "downloads": 2661, "source": "Hugging Face", - "score": -0.06676192990825087, - "first_commit": "2022-12-26 02:52:03", - "latest_commit": "2023-01-27 06:44:23", + "score": -0.06457522919907392, + "first_commit": "2024-07-26 01:30:21", + "latest_commit": "2024-07-26 02:30:17", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertModel" + "model_size": 70.6, + "model_architectures": "LlamaForCausalLM" }, { - "description": "PLaMo-13B Model Description PLaMo-13B is a LLaMA-based 13B model pre-trained on English and Japanese open datasets, developed by Preferred Networks, Inc. ", - "url": "https://huggingface.co/pfnet/plamo-13b", - "project_name": "plamo-13b", - "downloads": 3004, + "description": "rinna/japanese-wav2vec2-base Overview This is a Japanese wav2vec 2.0 Base model trained by rinna Co.", + "url": "https://huggingface.co/rinna/japanese-wav2vec2-base", + "project_name": "japanese-wav2vec2-base", + "downloads": 2633, "source": "Hugging Face", - "score": -0.0672489819657716, - "first_commit": "2023-09-25 12:47:05", - "latest_commit": "2023-10-10 15:24:54", + "score": -0.06487216781409127, + "first_commit": "2024-03-06 01:07:56", + "latest_commit": "2024-07-22 08:11:46", "languages": [], "model_or_dataset": "model", - "model_size": 13.1, - "model_architectures": "PlamoForCausalLM" + "model_size": 0.095, + "model_architectures": "Wav2Vec2ForPreTraining" }, { - "description": "Llama3 Swallow", - "url": "https://huggingface.co/tokyotech-llm/Llama-3-Swallow-70B-v0.1", - "project_name": "Llama-3-Swallow-70B-v0.1", - "downloads": 3002, + "description": "ELYZA-japanese-Llama-2-7b Model Description ELYZA-japanese-Llama-2-7b は、 Llama2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。 ", + "url": "https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b-fast-instruct", + "project_name": "ELYZA-japanese-Llama-2-7b-fast-instruct", + "downloads": 2586, "source": "Hugging Face", - "score": -0.06728040467916004, - "first_commit": "2024-06-14 05:56:33", - "latest_commit": "2024-07-01 06:24:32", + "score": -0.06537060048929896, + "first_commit": "2023-08-28 13:36:19", + "latest_commit": "2023-08-29 03:47:09", "languages": [], "model_or_dataset": "model", - "model_size": 70.6, + "model_size": null, "model_architectures": "LlamaForCausalLM" }, { @@ -3223,39 +3335,95 @@ "project_name": "small_parallel_enja", "stargazers_count": 92, "source": "GitHub", - "score": -0.06763623074817116, + "score": -0.06563500447821585, "first_commit": "2016-10-27 12:27:03", "latest_commit": "2019-09-11 14:00:17", "languages": [], "model_or_dataset": "dataset" }, { - "description": "Japanese-StableLM-Base-Beta-7B A cute robot wearing a kimono writes calligraphy with one single brush — Stable Diffusion XL Model Description japanese-stablelm-base-beta-7b is a 7B-parameter decoder-only language model based on Llama-2-7b that has been fine-tuned on a diverse collection of Japanese data, with the intent of maximizing downstream performance on Japanese language tasks.", - "url": "https://huggingface.co/stabilityai/japanese-stablelm-base-beta-7b", - "project_name": "japanese-stablelm-base-beta-7b", - "downloads": 2959, + "description": "LLaVA-JP Model Card Model detail Model type: LLaVA-JP is a vision-language model that can converse about input images.", + "url": "https://huggingface.co/toshi456/llava-jp-1.3b-v1.0", + "project_name": "llava-jp-1.3b-v1.0", + "downloads": 2544, "source": "Hugging Face", - "score": -0.06795599301701137, - "first_commit": "2023-10-30 07:43:36", - "latest_commit": "2023-12-19 06:43:01", + "score": -0.06581600841182499, + "first_commit": "2023-12-04 13:13:03", + "latest_commit": "2023-12-18 10:21:11", "languages": [], "model_or_dataset": "model", - "model_size": 6.74, + "model_size": 1.73, + "model_architectures": "LlavaGpt2ForCausalLM" + }, + { + "description": "Llama-3.1-8B-Instruct-gguf meta-llamaさんが公開しているMeta-Llama-3.1-8B-Instructのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Llama-3.1-8B-Instruct-gguf", + "project_name": "Llama-3.1-8B-Instruct-gguf", + "downloads": 2504, + "source": "Hugging Face", + "score": -0.06624020643327834, + "first_commit": "2024-07-23 16:33:06", + "latest_commit": "2024-07-24 21:04:40", + "languages": [], + "model_or_dataset": "model", + "model_size": 8.03, + "model_architectures": null + }, + { + "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", + "url": "https://huggingface.co/tokyotech-llm/Swallow-70b-instruct-hf", + "project_name": "Swallow-70b-instruct-hf", + "downloads": 2429, + "source": "Hugging Face", + "score": -0.06703557772350338, + "first_commit": "2023-12-11 07:23:47", + "latest_commit": "2024-06-29 08:56:31", + "languages": [], + "model_or_dataset": "model", + "model_size": 69.2, "model_architectures": "LlamaForCausalLM" }, { - "description": "このモデルはLuke-japanese-large-liteをファインチューニングしたものです。 ", - "url": "https://huggingface.co/Mizuiro-sakura/luke-japanese-large-sentiment-analysis-wrime", - "project_name": "luke-japanese-large-sentiment-analysis-wrime", - "downloads": 2928, + "description": "PLaMo-13B Model Description PLaMo-13B is a LLaMA-based 13B model pre-trained on English and Japanese open datasets, developed by Preferred Networks, Inc. ", + "url": "https://huggingface.co/pfnet/plamo-13b", + "project_name": "plamo-13b", + "downloads": 2335, "source": "Hugging Face", - "score": -0.06844304507453211, - "first_commit": "2023-03-13 12:40:08", - "latest_commit": "2023-05-15 12:58:08", + "score": -0.06803244307391876, + "first_commit": "2023-09-25 12:47:05", + "latest_commit": "2023-10-10 15:24:54", "languages": [], "model_or_dataset": "model", - "model_size": 0.41400000000000003, - "model_architectures": "LukeForSequenceClassification" + "model_size": 13.1, + "model_architectures": "PlamoForCausalLM" + }, + { + "description": "rinna/japanese-hubert-base Overview This is a Japanese HuBERT Base model trained by rinna Co.", + "url": "https://huggingface.co/rinna/japanese-hubert-base", + "project_name": "japanese-hubert-base", + "downloads": 2293, + "source": "Hugging Face", + "score": -0.06847785099644478, + "first_commit": "2023-04-28 07:39:44", + "latest_commit": "2024-07-20 08:55:38", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.09440000000000001, + "model_architectures": "HubertModel" + }, + { + "description": "bert-base-japanese-v3-marc_ja 「大規模言語モデル入門」の第5章で紹介している(感情分析)のモデルです。 ", + "url": "https://huggingface.co/llm-book/bert-base-japanese-v3-marc_ja", + "project_name": "bert-base-japanese-v3-marc_ja", + "downloads": 2290, + "source": "Hugging Face", + "score": -0.06850966584805379, + "first_commit": "2023-06-01 14:29:06", + "latest_commit": "2023-07-24 06:49:13", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "BertForSequenceClassification" }, { "description": "natto-py combines the Python programming language with MeCab, the part-of-speech and morphological analyzer for the Japanese language.", @@ -3263,7 +3431,7 @@ "project_name": "natto-py", "stargazers_count": 91, "source": "GitHub", - "score": -0.07056777276076893, + "score": -0.06857502503948555, "first_commit": "2014-10-24 20:56:40", "latest_commit": "2023-11-04 21:25:21", "languages": [ @@ -3279,7 +3447,7 @@ "project_name": "depccg", "stargazers_count": 91, "source": "GitHub", - "score": -0.07056777276076893, + "score": -0.06857502503948555, "first_commit": "2016-10-06 14:39:12", "latest_commit": "2023-08-26 16:03:23", "languages": [ @@ -3294,7 +3462,7 @@ "project_name": "oseti", "stargazers_count": 91, "source": "GitHub", - "score": -0.07056777276076893, + "score": -0.06857502503948555, "first_commit": "2019-02-12 02:03:26", "latest_commit": "2024-01-12 07:14:53", "languages": [ @@ -3303,166 +3471,152 @@ "model_or_dataset": null }, { - "description": "haqishen-Llama-3-8B-Japanese-Instruct-gguf haqishenさんが公開しているLlama-3-8B-Japanese-Instructのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/haqishen-Llama-3-8B-Japanese-Instruct-gguf", - "project_name": "haqishen-Llama-3-8B-Japanese-Instruct-gguf", - "downloads": 2742, + "description": "Converted from clu-ling/whisper-large-v2-japanese-5k-steps using CTranslate2.", + "url": "https://huggingface.co/zh-plus/faster-whisper-large-v2-japanese-5k-steps", + "project_name": "faster-whisper-large-v2-japanese-5k-steps", + "downloads": 2261, "source": "Hugging Face", - "score": -0.07136535741965648, - "first_commit": "2024-04-23 13:55:17", - "latest_commit": "2024-04-23 14:54:23", + "score": -0.06881720941360747, + "first_commit": "2023-07-03 08:29:37", + "latest_commit": "2023-07-03 18:42:31", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, + "model_size": null, "model_architectures": null }, { - "description": "Llama-3.1-70B-Japanese-Instruct-2407 Model Description This is a Japanese continually pre-trained model based on meta-llama/Meta-Llama-3.1-70B-Instruct.", - "url": "https://huggingface.co/cyberagent/Llama-3.1-70B-Japanese-Instruct-2407", - "project_name": "Llama-3.1-70B-Japanese-Instruct-2407", - "downloads": 2726, + "description": "japanese-large-lm-3.6b", + "url": "https://huggingface.co/line-corporation/japanese-large-lm-3.6b", + "project_name": "japanese-large-lm-3.6b", + "downloads": 2188, "source": "Hugging Face", - "score": -0.07161673912676396, - "first_commit": "2024-07-26 01:30:21", - "latest_commit": "2024-07-26 02:30:17", + "score": -0.06959137080275984, + "first_commit": "2023-07-21 00:48:05", + "latest_commit": "2023-08-17 01:06:17", "languages": [], "model_or_dataset": "model", - "model_size": 70.6, - "model_architectures": "LlamaForCausalLM" + "model_size": 3.68, + "model_architectures": "GPTNeoXForCausalLM" }, { - "description": "japanese-gpt2-xsmall", - "url": "https://huggingface.co/rinna/japanese-gpt2-xsmall", - "project_name": "japanese-gpt2-xsmall", - "downloads": 2707, + "description": "BERT base Japanese (character tokenization, whole word masking enabled)", + "url": "https://huggingface.co/tohoku-nlp/bert-base-japanese-char-whole-word-masking", + "project_name": "bert-base-japanese-char-whole-word-masking", + "downloads": 2175, "source": "Hugging Face", - "score": -0.07191525490395409, - "first_commit": "2021-07-26 02:52:54", - "latest_commit": "2024-07-20 07:48:11", + "score": -0.06972923515973217, + "first_commit": "2020-04-28 21:34:13", + "latest_commit": "2024-02-22 00:58:18", "languages": [], "model_or_dataset": "model", - "model_size": 0.0437, - "model_architectures": "GPT2LMHeadModel" + "model_size": null, + "model_architectures": "BertForMaskedLM" }, { - "description": "ELYZA-japanese-Llama-2-7b Model Description ELYZA-japanese-Llama-2-7b は、 Llama2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。 ", - "url": "https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b-fast-instruct", - "project_name": "ELYZA-japanese-Llama-2-7b-fast-instruct", - "downloads": 2651, + "description": "ELYZA-japanese-Llama-2-7b-fast-instruct-gguf ELYZAさんが公開しているELYZA-japanese-Llama-2-7b-fast-instructのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-7b-fast-instruct-gguf", + "project_name": "ELYZA-japanese-Llama-2-7b-fast-instruct-gguf", + "downloads": 2172, "source": "Hugging Face", - "score": -0.07279509087883024, - "first_commit": "2023-08-28 13:36:19", - "latest_commit": "2023-08-29 03:47:09", + "score": -0.06976105001134118, + "first_commit": "2023-08-29 15:31:01", + "latest_commit": "2023-11-16 14:27:48", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LlamaForCausalLM" + "model_size": 6.85, + "model_architectures": null }, { - "description": "Pytorch implementation and pre-trained Japanese model for CANINE, the efficient character-level transformer.", - "url": "https://github.com/octanove/shiba", - "project_name": "shiba", - "stargazers_count": 90, - "source": "GitHub", - "score": -0.07349931477336673, - "first_commit": "2021-06-24 20:17:27", - "latest_commit": "2023-11-03 10:01:53", - "languages": [ - "Python" - ], - "model_or_dataset": "model" - }, - { - "description": "おーぷん2ちゃんねるをクロールして作成した対話コーパス", - "url": "https://github.com/1never/open2ch-dialogue-corpus", - "project_name": "open2ch-dialogue-corpus", - "stargazers_count": 90, - "source": "GitHub", - "score": -0.07349931477336673, - "first_commit": "2019-09-13 11:21:53", - "latest_commit": "2021-06-07 00:06:23", - "languages": [ - "Python" - ], - "model_or_dataset": "dataset" + "description": "Leia-Swallow-7B LEIA is a training technique for autoregressive LLMs that effectively improves their performance in languages other than English by enhancing cross-lingual knowledge transfer from English to a target language.", + "url": "https://huggingface.co/leia-llm/Leia-Swallow-7b", + "project_name": "Leia-Swallow-7b", + "downloads": 2098, + "source": "Hugging Face", + "score": -0.07054581635102988, + "first_commit": "2024-04-17 07:12:28", + "latest_commit": "2024-04-17 10:29:56", + "languages": [], + "model_or_dataset": "model", + "model_size": 6.83, + "model_architectures": "LlamaForCausalLM" }, { - "description": "japanese-gpt-neox-3.6b-instruction-ppo Overview This repository provides a Japanese GPT-NeoX model of 3.6 billion parameters.", - "url": "https://huggingface.co/rinna/japanese-gpt-neox-3.6b-instruction-ppo", - "project_name": "japanese-gpt-neox-3.6b-instruction-ppo", - "downloads": 2564, + "description": "By clicking \"Agree\", you agree to the License Agreement and acknowledge Stability AI's Privacy Policy.", + "url": "https://huggingface.co/stabilityai/japanese-stablelm-2-instruct-1_6b", + "project_name": "japanese-stablelm-2-instruct-1_6b", + "downloads": 2093, "source": "Hugging Face", - "score": -0.07416197891122712, - "first_commit": "2023-05-30 01:50:48", - "latest_commit": "2024-07-20 07:58:49", + "score": -0.07059884110371155, + "first_commit": null, + "latest_commit": null, "languages": [], "model_or_dataset": "model", - "model_size": 3.76, - "model_architectures": "GPTNeoXForCausalLM" + "model_size": 1.64, + "model_architectures": null }, { - "description": "Llama-3.1-8B-Instruct-gguf meta-llamaさんが公開しているMeta-Llama-3.1-8B-Instructのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Llama-3.1-8B-Instruct-gguf", - "project_name": "Llama-3.1-8B-Instruct-gguf", - "downloads": 2527, + "description": "This dataset was created by automatically translating \"databricks-dolly-15k\" into Japanese.", + "url": "https://huggingface.co/datasets/kunishou/databricks-dolly-15k-ja", + "project_name": "databricks-dolly-15k-ja", + "downloads": 2079, "source": "Hugging Face", - "score": -0.07474329910891316, - "first_commit": "2024-07-23 16:33:06", - "latest_commit": "2024-07-24 21:04:40", + "score": -0.07074731041122023, + "first_commit": "2023-04-13 08:31:08", + "latest_commit": "2024-04-01 17:26:37", "languages": [], - "model_or_dataset": "model", - "model_size": 8.03, + "model_or_dataset": "dataset", + "model_size": null, "model_architectures": null }, { - "description": "Japanese Stable LM Instruct Gamma 7B Model Description", - "url": "https://huggingface.co/stabilityai/japanese-stablelm-instruct-gamma-7b", - "project_name": "japanese-stablelm-instruct-gamma-7b", - "downloads": 2465, + "description": "Gemma-Mling: Multilingual Gemma Update @ 2024.04.15: First release of Gemma-Mling 7B model Original Gemma Model Page:", + "url": "https://huggingface.co/beomi/gemma-mling-7b", + "project_name": "gemma-mling-7b", + "downloads": 2070, "source": "Hugging Face", - "score": -0.07571740322395462, - "first_commit": "2023-10-16 08:55:06", - "latest_commit": "2024-01-24 05:54:38", + "score": -0.07084275496604724, + "first_commit": "2024-04-15 05:37:05", + "latest_commit": "2024-04-18 14:28:20", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": "MistralForCausalLM" + "model_size": 8.54, + "model_architectures": "GemmaForCausalLM" }, { - "description": "rinna/japanese-hubert-base Overview This is a Japanese HuBERT Base model trained by rinna Co.", - "url": "https://huggingface.co/rinna/japanese-hubert-base", - "project_name": "japanese-hubert-base", - "downloads": 2448, + "description": "Leia-Swallow-13B LEIA is a training technique for autoregressive LLMs that effectively improves their performance in languages other than English by enhancing cross-lingual knowledge transfer from English to a target language.", + "url": "https://huggingface.co/leia-llm/Leia-Swallow-13b", + "project_name": "Leia-Swallow-13b", + "downloads": 2058, "source": "Hugging Face", - "score": -0.07598449628775632, - "first_commit": "2023-04-28 07:39:44", - "latest_commit": "2024-07-20 08:55:38", + "score": -0.07097001437248324, + "first_commit": "2024-04-17 07:32:11", + "latest_commit": "2024-04-18 05:21:10", "languages": [], "model_or_dataset": "model", - "model_size": 0.09440000000000001, - "model_architectures": "HubertModel" + "model_size": 13.1, + "model_architectures": "LlamaForCausalLM" }, { - "description": "sbert-jsnli-luke-japanese-base-lite This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.", - "url": "https://huggingface.co/oshizo/sbert-jsnli-luke-japanese-base-lite", - "project_name": "sbert-jsnli-luke-japanese-base-lite", - "downloads": 2401, + "description": "bilingual-gpt-neox-4b Overview This repository provides an English-Japanese bilingual GPT-NeoX model of 3.8 billion parameters.", + "url": "https://huggingface.co/rinna/bilingual-gpt-neox-4b", + "project_name": "bilingual-gpt-neox-4b", + "downloads": 2048, "source": "Hugging Face", - "score": -0.07672293005238452, - "first_commit": "2023-01-10 11:53:15", - "latest_commit": "2023-01-10 12:36:12", + "score": -0.07107606387784658, + "first_commit": "2023-07-31 02:34:03", + "latest_commit": "2024-07-20 08:02:07", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LukeModel" + "model_size": 3.95, + "model_architectures": "GPTNeoXForCausalLM" }, { "description": "wav2vec2-base-asr", "url": "https://huggingface.co/TKU410410103/wav2vec2-base-japanese-asr", "project_name": "wav2vec2-base-japanese-asr", - "downloads": 2326, + "downloads": 2032, "source": "Hugging Face", - "score": -0.0779012818044508, + "score": -0.07124574308642792, "first_commit": "2024-04-14 10:22:21", "latest_commit": "2024-04-14 14:00:30", "languages": [], @@ -3471,40 +3625,68 @@ "model_architectures": "Wav2Vec2ForCTC" }, { - "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", - "url": "https://huggingface.co/tokyotech-llm/Swallow-70b-instruct-hf", - "project_name": "Swallow-70b-instruct-hf", - "downloads": 2283, + "description": "FINGU-AI/FinguAI-Chat-v1 Overview The FINGU-AI/FinguAI-Chat-v1 model offers a specialized curriculum tailored to English, Korean, and Japanese speakers interested in finance, investment, and legal frameworks.", + "url": "https://huggingface.co/FINGU-AI/FinguAI-Chat-v1", + "project_name": "FinguAI-Chat-v1", + "downloads": 2007, "source": "Hugging Face", - "score": -0.07857687014230214, - "first_commit": "2023-12-11 07:23:47", - "latest_commit": "2024-06-29 08:56:31", + "score": -0.07151086684983626, + "first_commit": "2024-03-21 07:08:05", + "latest_commit": "2024-03-22 09:36:44", "languages": [], "model_or_dataset": "model", - "model_size": 69.2, - "model_architectures": "LlamaForCausalLM" + "model_size": 0.464, + "model_architectures": "Qwen2ForCausalLM" }, { - "description": "Converted from clu-ling/whisper-large-v2-japanese-5k-steps using CTranslate2.", - "url": "https://huggingface.co/zh-plus/faster-whisper-large-v2-japanese-5k-steps", - "project_name": "faster-whisper-large-v2-japanese-5k-steps", - "downloads": 2263, + "description": "Pytorch implementation and pre-trained Japanese model for CANINE, the efficient character-level transformer.", + "url": "https://github.com/octanove/shiba", + "project_name": "shiba", + "stargazers_count": 90, + "source": "GitHub", + "score": -0.07151504560075525, + "first_commit": "2021-06-24 20:17:27", + "latest_commit": "2023-11-03 10:01:53", + "languages": [ + "Python" + ], + "model_or_dataset": "model" + }, + { + "description": "おーぷん2ちゃんねるをクロールして作成した対話コーパス", + "url": "https://github.com/1never/open2ch-dialogue-corpus", + "project_name": "open2ch-dialogue-corpus", + "stargazers_count": 90, + "source": "GitHub", + "score": -0.07151504560075525, + "first_commit": "2019-09-13 11:21:53", + "latest_commit": "2021-06-07 00:06:23", + "languages": [ + "Python" + ], + "model_or_dataset": "dataset" + }, + { + "description": "Llama-3-Swallow-70B-Instruct-v0.1-gguf tokyotech-llmさんが公開しているLlama-3-Swallow-70B-Instruct-v0.1のggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Llama-3-Swallow-70B-Instruct-v0.1-gguf", + "project_name": "Llama-3-Swallow-70B-Instruct-v0.1-gguf", + "downloads": 2001, "source": "Hugging Face", - "score": -0.07889109727618647, - "first_commit": "2023-07-03 08:29:37", - "latest_commit": "2023-07-03 18:42:31", + "score": -0.07157449655305427, + "first_commit": "2024-07-01 14:21:29", + "latest_commit": "2024-07-07 05:04:16", "languages": [], "model_or_dataset": "model", - "model_size": null, + "model_size": 70.6, "model_architectures": null }, { "description": "hubert-base-asr", "url": "https://huggingface.co/TKU410410103/hubert-base-japanese-asr", "project_name": "hubert-base-japanese-asr", - "downloads": 2257, + "downloads": 1984, "source": "Hugging Face", - "score": -0.07898536541635177, + "score": -0.07175478071217195, "first_commit": "2024-04-09 06:01:43", "latest_commit": "2024-04-14 13:20:43", "languages": [], @@ -3513,358 +3695,306 @@ "model_architectures": "HubertForCTC" }, { - "description": "Llama-3.1-8B-EZO-1.1-it-gguf HODACHIさんが公開しているLlama-3.1-8B-EZO-1.1-itのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Llama-3.1-8B-EZO-1.1-it-gguf", - "project_name": "Llama-3.1-8B-EZO-1.1-it-gguf", - "downloads": 2255, + "description": "Stockmark-13b-instruct Stockmark-13b-instruct is an instruction-tuned version of Stockmark-13b, a 13 billion parameter Japanese LLM.", + "url": "https://huggingface.co/stockmark/stockmark-13b-instruct", + "project_name": "stockmark-13b-instruct", + "downloads": 1976, "source": "Hugging Face", - "score": -0.07901678812974021, - "first_commit": "2024-07-31 11:06:36", - "latest_commit": "2024-07-31 12:47:45", + "score": -0.07183962031646261, + "first_commit": "2023-11-08 16:56:34", + "latest_commit": "2023-11-08 17:02:17", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": null + "model_size": 13.2, + "model_architectures": "LlamaForCausalLM" }, { - "description": "bert-base-japanese-v3-marc_ja 「大規模言語モデル入門」の第5章で紹介している(感情分析)のモデルです。 ", - "url": "https://huggingface.co/llm-book/bert-base-japanese-v3-marc_ja", - "project_name": "bert-base-japanese-v3-marc_ja", - "downloads": 2254, + "description": "Kotoba-Whisper Kotoba-Whisper is a collection of distilled Whisper models for Japanese ASR, developed through the collaboration bewteen Asahi Ushio and Kotoba Technologies.", + "url": "https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0", + "project_name": "kotoba-whisper-v1.0", + "downloads": 1960, "source": "Hugging Face", - "score": -0.07903249948643443, - "first_commit": "2023-06-01 14:29:06", - "latest_commit": "2023-07-24 06:49:13", + "score": -0.07200929952504395, + "first_commit": "2024-04-14 08:53:48", + "latest_commit": "2024-05-08 12:40:53", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForSequenceClassification" + "model_size": 0.756, + "model_architectures": "WhisperForConditionalGeneration" }, { - "description": "Gemma-Mling: Multilingual Gemma Update @ 2024.04.15: First release of Gemma-Mling 7B model Original Gemma Model Page:", - "url": "https://huggingface.co/beomi/gemma-mling-7b", - "project_name": "gemma-mling-7b", - "downloads": 2243, + "description": "calm3-22b-RP-GGUF 概要 Aratako/calm3-22b-RPの量子化済みGGUF版です。", + "url": "https://huggingface.co/Aratako/calm3-22b-RP-GGUF", + "project_name": "calm3-22b-RP-GGUF", + "downloads": 1936, "source": "Hugging Face", - "score": -0.07920532441007082, - "first_commit": "2024-04-15 05:37:05", - "latest_commit": "2024-04-18 14:28:20", + "score": -0.07226381833791597, + "first_commit": "2024-08-21 01:13:32", + "latest_commit": "2024-08-21 13:26:35", "languages": [], "model_or_dataset": "model", - "model_size": 8.54, - "model_architectures": "GemmaForCausalLM" - }, - { - "description": "A Python Module for JUMAN++/KNP", - "url": "https://github.com/ku-nlp/pyknp", - "project_name": "pyknp", - "stargazers_count": 88, - "source": "GitHub", - "score": -0.0793623987985623, - "first_commit": "2015-04-08 15:25:47", - "latest_commit": "2024-07-06 15:16:48", - "languages": [ - "Python" - ], - "model_or_dataset": null + "model_size": 22.5, + "model_architectures": null }, { - "description": "STAIR captions: large-scale Japanese image caption dataset", - "url": "https://github.com/STAIR-Lab-CIT/STAIR-captions", - "project_name": "STAIR-captions", - "stargazers_count": 88, - "source": "GitHub", - "score": -0.0793623987985623, - "first_commit": "2017-02-21 16:49:14", - "latest_commit": "2018-07-04 18:24:35", + "description": "Fish Speech V1.2 Fish Speech V1.2 is a leading text-to-speech (TTS) model trained on 300k hours of English, Chinese, and Japanese audio data.", + "url": "https://huggingface.co/fishaudio/fish-speech-1.2-sft", + "project_name": "fish-speech-1.2-sft", + "downloads": 1903, + "source": "Hugging Face", + "score": -0.07261378170561499, + "first_commit": "2024-07-18 08:00:29", + "latest_commit": "2024-08-02 08:13:06", "languages": [], - "model_or_dataset": "dataset" - }, - { - "description": "NMeCab: About Japanese morphological analyzer on .NET", - "url": "https://github.com/komutan/NMeCab", - "project_name": "NMeCab", - "stargazers_count": 88, - "source": "GitHub", - "score": -0.0793623987985623, - "first_commit": "2014-04-24 17:34:29", - "latest_commit": "2024-03-31 03:51:55", - "languages": [ - "C#" - ], - "model_or_dataset": "dataset" + "model_or_dataset": "model", + "model_size": null, + "model_architectures": null }, { - "description": "japanese-large-lm-3.6b", - "url": "https://huggingface.co/line-corporation/japanese-large-lm-3.6b", - "project_name": "japanese-large-lm-3.6b", - "downloads": 2174, + "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", + "url": "https://huggingface.co/tokyotech-llm/Swallow-13b-hf", + "project_name": "Swallow-13b-hf", + "downloads": 1800, "source": "Hugging Face", - "score": -0.08028940802197179, - "first_commit": "2023-07-21 00:48:05", - "latest_commit": "2023-08-17 01:06:17", + "score": -0.07370609161085738, + "first_commit": "2023-11-16 15:40:49", + "latest_commit": "2024-06-29 08:56:21", "languages": [], "model_or_dataset": "model", - "model_size": 3.68, - "model_architectures": "GPTNeoXForCausalLM" + "model_size": null, + "model_architectures": "LlamaForCausalLM" }, { - "description": "clip-japanese-base This is a Japanese CLIP (Contrastive Language-Image Pre-training) model developed by LY Corporation.", - "url": "https://huggingface.co/line-corporation/clip-japanese-base", - "project_name": "clip-japanese-base", - "downloads": 2124, + "description": "recruit-jp/japanese-clip-vit-b-32-roberta-base Overview Developed by: Recruit Co.", + "url": "https://huggingface.co/recruit-jp/japanese-clip-vit-b-32-roberta-base", + "project_name": "japanese-clip-vit-b-32-roberta-base", + "downloads": 1795, "source": "Hugging Face", - "score": -0.08107497585668265, - "first_commit": "2024-04-24 01:36:22", - "latest_commit": "2024-05-10 03:07:04", + "score": -0.07375911636353905, + "first_commit": "2023-12-20 06:06:12", + "latest_commit": "2024-01-22 07:41:59", "languages": [], "model_or_dataset": "model", - "model_size": 0.197, - "model_architectures": "CLYPModel" + "model_size": 0.198, + "model_architectures": "JapaneseCLIPModel" }, { - "description": "FINGU-AI/FinguAI-Chat-v1 Overview The FINGU-AI/FinguAI-Chat-v1 model offers a specialized curriculum tailored to English, Korean, and Japanese speakers interested in finance, investment, and legal frameworks.", - "url": "https://huggingface.co/FINGU-AI/FinguAI-Chat-v1", - "project_name": "FinguAI-Chat-v1", - "downloads": 2110, + "description": "OpenCALM-Large Model Description OpenCALM is a suite of decoder-only language models pre-trained on Japanese datasets, developed by", + "url": "https://huggingface.co/cyberagent/open-calm-large", + "project_name": "open-calm-large", + "downloads": 1779, "source": "Hugging Face", - "score": -0.08129493485040169, - "first_commit": "2024-03-21 07:08:05", - "latest_commit": "2024-03-22 09:36:44", + "score": -0.07392879557212038, + "first_commit": "2023-05-15 06:50:24", + "latest_commit": "2023-05-18 01:11:13", "languages": [], "model_or_dataset": "model", - "model_size": 0.464, - "model_architectures": "Qwen2ForCausalLM" + "model_size": null, + "model_architectures": "GPTNeoXForCausalLM" }, { - "description": "ElanMT ElanMT-BT-ja-en is a Japanese to English translation model developed by ELAN MITSUA Project / Abstract Engine.", - "url": "https://huggingface.co/Mitsua/elan-mt-bt-ja-en", - "project_name": "elan-mt-bt-ja-en", - "downloads": 2100, + "description": "alabnii/jmedroberta-base-sentencepiece Model description This is a Japanese RoBERTa base model pre-trained on academic articles in medical sciences collected by Japan Science and Technology Agency (JST).", + "url": "https://huggingface.co/alabnii/jmedroberta-base-sentencepiece", + "project_name": "jmedroberta-base-sentencepiece", + "downloads": 1776, "source": "Hugging Face", - "score": -0.08145204841734387, - "first_commit": "2024-05-20 01:56:12", - "latest_commit": "2024-05-20 01:56:57", + "score": -0.07396061042372938, + "first_commit": "2022-12-22 17:20:33", + "latest_commit": "2023-03-21 23:57:37", "languages": [], "model_or_dataset": "model", - "model_size": 0.0606, - "model_architectures": "MarianMTModel" + "model_size": 0.109, + "model_architectures": "BertForMaskedLM" }, { - "description": "Leia-Swallow-7B LEIA is a training technique for autoregressive LLMs that effectively improves their performance in languages other than English by enhancing cross-lingual knowledge transfer from English to a target language.", - "url": "https://huggingface.co/leia-llm/Leia-Swallow-7b", - "project_name": "Leia-Swallow-7b", - "downloads": 2096, + "description": "自動生成のマルチターンデータセット オープンなデータソースから､Calm3-22bを使ってQ&Aを自動生成したものです｡ 一部の計算には東京工業大学のスーパーコンピュータTSUBAME4.0を利用しました｡ データソース はじめの質問(q1)を､種々のデータソースから収集しました｡その後のやりとりはすべて､Calmが生成しました｡質問文については､元データのライセンスに準拠します｡ oasst2-33k-ja apache 2.0 databricks-dolly-15k-ja cc-by-sa-3.0 minnade CC0 cyberagent/chatbot-arena-ja-calm2-7b-chat-experimental cc-by-4.0", + "url": "https://huggingface.co/datasets/kanhatakeyama/AutoMultiTurnByCalm3-22B", + "project_name": "AutoMultiTurnByCalm3-22B", + "downloads": 1776, "source": "Hugging Face", - "score": -0.08151489384412072, - "first_commit": "2024-04-17 07:12:28", - "latest_commit": "2024-04-17 10:29:56", + "score": -0.07396061042372938, + "first_commit": "2024-07-17 09:53:20", + "latest_commit": "2024-07-17 10:03:02", "languages": [], - "model_or_dataset": "model", - "model_size": 6.83, - "model_architectures": "LlamaForCausalLM" + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null }, { - "description": "Llama-3-Swallow-70B-Instruct-v0.1-gguf tokyotech-llmさんが公開しているLlama-3-Swallow-70B-Instruct-v0.1のggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Llama-3-Swallow-70B-Instruct-v0.1-gguf", - "project_name": "Llama-3-Swallow-70B-Instruct-v0.1-gguf", - "downloads": 2091, + "description": "bert-base-japanese-v3-jsts 「大規模言語モデル入門」の第5章で紹介している(意味類似度計算)のモデルです。 ", + "url": "https://huggingface.co/llm-book/bert-base-japanese-v3-jsts", + "project_name": "bert-base-japanese-v3-jsts", + "downloads": 1730, "source": "Hugging Face", - "score": -0.08159345062759181, - "first_commit": "2024-07-01 14:21:29", - "latest_commit": "2024-07-07 05:04:16", + "score": -0.07444843814840074, + "first_commit": "2023-06-11 15:27:32", + "latest_commit": "2023-07-29 11:27:18", "languages": [], "model_or_dataset": "model", - "model_size": 70.6, - "model_architectures": null + "model_size": null, + "model_architectures": "BertForSequenceClassification" }, { - "description": "By clicking \"Agree\", you agree to the License Agreement and acknowledge Stability AI's Privacy Policy.", - "url": "https://huggingface.co/stabilityai/japanese-stablelm-2-instruct-1_6b", - "project_name": "japanese-stablelm-2-instruct-1_6b", - "downloads": 2086, + "description": "upskyy/gte-korean-base This model is korsts and kornli finetuning model from Alibaba-NLP/gte-multilingual-base.", + "url": "https://huggingface.co/upskyy/gte-base-korean", + "project_name": "gte-base-korean", + "downloads": 1726, "source": "Hugging Face", - "score": -0.0816720074110629, - "first_commit": null, - "latest_commit": null, + "score": -0.07449085795054608, + "first_commit": "2024-08-08 14:34:44", + "latest_commit": "2024-08-08 15:29:27", "languages": [], "model_or_dataset": "model", - "model_size": 1.64, - "model_architectures": null + "model_size": 0.305, + "model_architectures": "NewModel" }, { - "description": "Kotoba-Whisper Kotoba-Whisper is a collection of distilled Whisper models for Japanese ASR, developed through the collaboration bewteen Asahi Ushio and Kotoba Technologies.", - "url": "https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0", - "project_name": "kotoba-whisper-v1.0", - "downloads": 2085, + "description": "Model Card for Japanese character-level DeBERTa V2 base Model description This is a Japanese DeBERTa V2 base model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.", + "url": "https://huggingface.co/ku-nlp/deberta-v2-base-japanese-char-wwm", + "project_name": "deberta-v2-base-japanese-char-wwm", + "downloads": 1700, "source": "Hugging Face", - "score": -0.08168771876775711, - "first_commit": "2024-04-14 08:53:48", - "latest_commit": "2024-05-08 12:40:53", + "score": -0.07476658666449076, + "first_commit": "2023-01-18 13:55:30", + "latest_commit": "2023-03-26 03:32:27", "languages": [], "model_or_dataset": "model", - "model_size": 0.756, - "model_architectures": "WhisperForConditionalGeneration" + "model_size": 0.122, + "model_architectures": "DebertaV2ForMaskedLM" }, { - "description": "Model Card for Japanese character-level DeBERTa V2 tiny Model description This is a Japanese DeBERTa V2 tiny model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.", - "url": "https://huggingface.co/ku-nlp/deberta-v2-tiny-japanese-char-wwm", - "project_name": "deberta-v2-tiny-japanese-char-wwm", - "downloads": 2084, + "description": "uniTKU-hubert-japanese-asr", + "url": "https://huggingface.co/TKU410410103/uniTKU-hubert-japanese-asr", + "project_name": "uniTKU-hubert-japanese-asr", + "downloads": 1694, "source": "Hugging Face", - "score": -0.08170343012445133, - "first_commit": "2023-01-05 08:48:29", - "latest_commit": "2023-03-23 07:31:19", + "score": -0.07483021636770876, + "first_commit": "2024-04-20 14:59:52", + "latest_commit": "2024-04-22 18:37:33", "languages": [], "model_or_dataset": "model", - "model_size": 0.0101, - "model_architectures": "DebertaV2ForMaskedLM" + "model_size": 0.0945, + "model_architectures": "HubertForCTC" }, { - "description": "HODACHI-EZO-Common-9B-gemma-2-it-gguf HODACHIさんが公開しているEZO-Common-9B-gemma-2-itのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/HODACHI-EZO-Common-9B-gemma-2-it-gguf", - "project_name": "HODACHI-EZO-Common-9B-gemma-2-it-gguf", - "downloads": 2061, + "description": "hubert-large-asr", + "url": "https://huggingface.co/TKU410410103/hubert-large-japanese-asr", + "project_name": "hubert-large-japanese-asr", + "downloads": 1687, "source": "Hugging Face", - "score": -0.08206479132841833, - "first_commit": "2024-07-15 15:42:39", - "latest_commit": "2024-07-15 16:20:33", + "score": -0.0749044510214631, + "first_commit": "2024-04-09 03:01:08", + "latest_commit": "2024-04-14 13:21:01", "languages": [], "model_or_dataset": "model", - "model_size": 9.24, - "model_architectures": null + "model_size": 0.316, + "model_architectures": "HubertForCTC" }, { - "description": "Leia-Swallow-13B LEIA is a training technique for autoregressive LLMs that effectively improves their performance in languages other than English by enhancing cross-lingual knowledge transfer from English to a target language.", - "url": "https://huggingface.co/leia-llm/Leia-Swallow-13b", - "project_name": "Leia-Swallow-13b", - "downloads": 2056, + "description": "ELYZA-japanese-Llama-2-13b Model Description ELYZA-japanese-Llama-2-13b は、 Llama 2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。", + "url": "https://huggingface.co/elyza/ELYZA-japanese-Llama-2-13b", + "project_name": "ELYZA-japanese-Llama-2-13b", + "downloads": 1677, "source": "Hugging Face", - "score": -0.08214334811188942, - "first_commit": "2024-04-17 07:32:11", - "latest_commit": "2024-04-18 05:21:10", + "score": -0.07501050052682644, + "first_commit": "2023-12-25 16:38:08", + "latest_commit": "2023-12-27 01:40:43", "languages": [], "model_or_dataset": "model", - "model_size": 13.1, + "model_size": null, "model_architectures": "LlamaForCausalLM" }, { - "description": "alpacaデータセットを日本語化したものです", - "url": "https://github.com/shi3z/alpaca_ja", - "project_name": "alpaca_ja", - "stargazers_count": 87, - "source": "GitHub", - "score": -0.0822939408111601, - "first_commit": "2023-04-01 07:03:33", - "latest_commit": "2023-05-17 15:43:50", - "languages": [], - "model_or_dataset": "dataset" - }, - { - "description": "stockmark/stockmark-13b Stockmark-13b is a 13 billion parameter LLM pretrained from scratch based on Japanese corpus of about 220B tokens.", - "url": "https://huggingface.co/stockmark/stockmark-13b", - "project_name": "stockmark-13b", - "downloads": 2034, + "description": "BERTによる日本語固有表現抽出のモデル BertForTokenClassificationを用いて、日本語の文から固有表現を抽出します。 ", + "url": "https://huggingface.co/jurabi/bert-ner-japanese", + "project_name": "bert-ner-japanese", + "downloads": 1667, "source": "Hugging Face", - "score": -0.08248899795916219, - "first_commit": "2023-10-21 06:53:06", - "latest_commit": "2024-05-17 06:15:56", + "score": -0.07511655003218978, + "first_commit": "2022-09-26 07:46:38", + "latest_commit": "2022-09-26 12:13:44", "languages": [], "model_or_dataset": "model", - "model_size": 13.2, - "model_architectures": "LlamaForCausalLM" + "model_size": null, + "model_architectures": "BertForTokenClassification" }, { - "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", - "url": "https://huggingface.co/tokyotech-llm/Swallow-13b-hf", - "project_name": "Swallow-13b-hf", - "downloads": 2009, + "description": "japanese-gpt-1b This repository provides a 1.3B-parameter Japanese GPT model.", + "url": "https://huggingface.co/rinna/japanese-gpt-1b", + "project_name": "japanese-gpt-1b", + "downloads": 1666, "source": "Hugging Face", - "score": -0.08288178187651761, - "first_commit": "2023-11-16 15:40:49", - "latest_commit": "2024-06-29 08:56:21", + "score": -0.07512715498272611, + "first_commit": "2022-01-20 02:30:19", + "latest_commit": "2024-07-20 07:52:31", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LlamaForCausalLM" + "model_size": 1.33, + "model_architectures": "GPT2LMHeadModel" }, { - "description": "Fish Speech V1.2 Fish Speech V1.2 is a leading text-to-speech (TTS) model trained on 300k hours of English, Chinese, and Japanese audio data.", - "url": "https://huggingface.co/fishaudio/fish-speech-1.2-sft", - "project_name": "fish-speech-1.2-sft", - "downloads": 1994, + "description": "Japanese-StableLM-Base-Alpha-7B \"A parrot able to speak Japanese, ukiyoe, edo period\" — Stable Diffusion XL Model Description japanese-stablelm-base-alpha-7b is a 7B-parameter decoder-only language model pre-trained on a diverse collection of Japanese and English datasets which focus on maximizing Japanese language modeling performance and Japanese downstream task performance.", + "url": "https://huggingface.co/stabilityai/japanese-stablelm-base-alpha-7b", + "project_name": "japanese-stablelm-base-alpha-7b", + "downloads": 1647, "source": "Hugging Face", - "score": -0.08311745222693087, - "first_commit": "2024-07-18 08:00:29", - "latest_commit": "2024-08-02 08:13:06", + "score": -0.07532864904291646, + "first_commit": "2023-08-09 14:30:09", + "latest_commit": "2023-08-22 09:36:29", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "JapaneseStableLMAlphaForCausalLM" }, { - "description": "Stockmark-13b-instruct Stockmark-13b-instruct is an instruction-tuned version of Stockmark-13b, a 13 billion parameter Japanese LLM.", - "url": "https://huggingface.co/stockmark/stockmark-13b-instruct", - "project_name": "stockmark-13b-instruct", - "downloads": 1994, + "description": "OpenCALM-1B Model Description OpenCALM is a suite of decoder-only language models pre-trained on Japanese datasets, developed by", + "url": "https://huggingface.co/cyberagent/open-calm-1b", + "project_name": "open-calm-1b", + "downloads": 1641, "source": "Hugging Face", - "score": -0.08311745222693087, - "first_commit": "2023-11-08 16:56:34", - "latest_commit": "2023-11-08 17:02:17", + "score": -0.07539227874613445, + "first_commit": "2023-05-15 07:00:18", + "latest_commit": "2023-05-18 01:11:30", "languages": [], "model_or_dataset": "model", - "model_size": 13.2, - "model_architectures": "LlamaForCausalLM" + "model_size": null, + "model_architectures": "GPTNeoXForCausalLM" }, { - "description": "uniTKU-hubert-japanese-asr", - "url": "https://huggingface.co/TKU410410103/uniTKU-hubert-japanese-asr", - "project_name": "uniTKU-hubert-japanese-asr", - "downloads": 1917, + "description": "Llama-3.1-8B-EZO-1.1-it-gguf HODACHIさんが公開しているLlama-3.1-8B-EZO-1.1-itのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Llama-3.1-8B-EZO-1.1-it-gguf", + "project_name": "Llama-3.1-8B-EZO-1.1-it-gguf", + "downloads": 1627, "source": "Hugging Face", - "score": -0.08432722669238558, - "first_commit": "2024-04-20 14:59:52", - "latest_commit": "2024-04-22 18:37:33", + "score": -0.07554074805364314, + "first_commit": "2024-07-31 11:06:36", + "latest_commit": "2024-07-31 12:47:45", "languages": [], "model_or_dataset": "model", - "model_size": 0.0945, - "model_architectures": "HubertForCTC" + "model_size": 8.03, + "model_architectures": null }, { - "description": "hubert-large-asr", - "url": "https://huggingface.co/TKU410410103/hubert-large-japanese-asr", - "project_name": "hubert-large-japanese-asr", - "downloads": 1915, + "description": "luke-japanese-large-lite luke-japanese is the Japanese version of LUKE (Language Understanding with Knowledge-based Embeddings), a pre-trained knowledge-enhanced contextualized representation of words and entities.", + "url": "https://huggingface.co/studio-ousia/luke-japanese-large-lite", + "project_name": "luke-japanese-large-lite", + "downloads": 1621, "source": "Hugging Face", - "score": -0.08435864940577402, - "first_commit": "2024-04-09 03:01:08", - "latest_commit": "2024-04-14 13:21:01", + "score": -0.07560437775686113, + "first_commit": "2022-11-07 14:26:40", + "latest_commit": "2022-11-09 11:19:36", "languages": [], "model_or_dataset": "model", - "model_size": 0.316, - "model_architectures": "HubertForCTC" - }, - { - "description": "GUIで動作する文書校正ツール GUI tool for textlinting.", - "url": "https://github.com/gecko655/proofreading-tool", - "project_name": "proofreading-tool", - "stargazers_count": 86, - "source": "GitHub", - "score": -0.08522548282375787, - "first_commit": "2021-04-08 12:10:36", - "latest_commit": "2024-06-22 20:18:09", - "languages": [ - "JavaScript" - ], - "model_or_dataset": null + "model_size": null, + "model_architectures": "LukeForMaskedLM" }, { "description": "ELYZA-tasks-100: 日本語instructionモデル評価データセット Data Description 本データセットはinstruction-tuningを行ったモデルの評価用データセットです。", "url": "https://huggingface.co/datasets/elyza/ELYZA-tasks-100", "project_name": "ELYZA-tasks-100", - "downloads": 1845, + "downloads": 1616, "source": "Hugging Face", - "score": -0.08545844437436922, + "score": -0.07565740250954281, "first_commit": "2023-08-28 09:01:44", "latest_commit": "2023-12-27 18:17:36", "languages": [], @@ -3873,516 +4003,498 @@ "model_architectures": null }, { - "description": "BERT base Japanese (character tokenization, whole word masking enabled)", - "url": "https://huggingface.co/tohoku-nlp/bert-base-japanese-char-whole-word-masking", - "project_name": "bert-base-japanese-char-whole-word-masking", - "downloads": 1830, + "description": "HODACHI-EZO-Common-9B-gemma-2-it-gguf HODACHIさんが公開しているEZO-Common-9B-gemma-2-itのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/HODACHI-EZO-Common-9B-gemma-2-it-gguf", + "project_name": "HODACHI-EZO-Common-9B-gemma-2-it-gguf", + "downloads": 1582, "source": "Hugging Face", - "score": -0.08569411472478247, - "first_commit": "2020-04-28 21:34:13", - "latest_commit": "2024-02-22 00:58:18", + "score": -0.07601797082777816, + "first_commit": "2024-07-15 15:42:39", + "latest_commit": "2024-07-15 16:20:33", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForMaskedLM" + "model_size": 9.24, + "model_architectures": null }, { - "description": "BERTによる日本語固有表現抽出のモデル BertForTokenClassificationを用いて、日本語の文から固有表現を抽出します。 ", - "url": "https://huggingface.co/jurabi/bert-ner-japanese", - "project_name": "bert-ner-japanese", - "downloads": 1818, + "description": "ELYZA-japanese-Llama-2-13b-fast-instruct Model Description ELYZA-japanese-Llama-2-13b は、 Llama 2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。 ", + "url": "https://huggingface.co/elyza/ELYZA-japanese-Llama-2-13b-fast-instruct", + "project_name": "ELYZA-japanese-Llama-2-13b-fast-instruct", + "downloads": 1577, "source": "Hugging Face", - "score": -0.08588265100511308, - "first_commit": "2022-09-26 07:46:38", - "latest_commit": "2022-09-26 12:13:44", + "score": -0.07607099558045982, + "first_commit": "2023-12-25 18:14:10", + "latest_commit": "2023-12-27 01:41:51", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "BertForTokenClassification" + "model_architectures": "LlamaForCausalLM" }, { - "description": "bert-base-japanese-v3-jsts 「大規模言語モデル入門」の第5章で紹介している(意味類似度計算)のモデルです。 ", - "url": "https://huggingface.co/llm-book/bert-base-japanese-v3-jsts", - "project_name": "bert-base-japanese-v3-jsts", - "downloads": 1793, + "description": "bert-base-japanese-upos Model Description", + "url": "https://huggingface.co/KoichiYasuoka/bert-base-japanese-upos", + "project_name": "bert-base-japanese-upos", + "downloads": 1553, "source": "Hugging Face", - "score": -0.0862754349224685, - "first_commit": "2023-06-11 15:27:32", - "latest_commit": "2023-07-29 11:27:18", + "score": -0.07632551439333184, + "first_commit": "2021-08-26 23:02:50", + "latest_commit": "2022-09-18 19:43:26", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "BertForSequenceClassification" + "model_architectures": "BertForTokenClassification" }, { - "description": "japanese-gpt-1b This repository provides a 1.3B-parameter Japanese GPT model.", - "url": "https://huggingface.co/rinna/japanese-gpt-1b", - "project_name": "japanese-gpt-1b", - "downloads": 1746, + "description": "This dataset contains a diverse set of natural Japanese speech, collected from terrestrial television streams.", + "url": "https://huggingface.co/datasets/reazon-research/reazonspeech", + "project_name": "reazonspeech", + "downloads": 1539, "source": "Hugging Face", - "score": -0.08701386868709671, - "first_commit": "2022-01-20 02:30:19", - "latest_commit": "2024-07-20 07:52:31", + "score": -0.0764739837008405, + "first_commit": null, + "latest_commit": null, "languages": [], - "model_or_dataset": "model", - "model_size": 1.33, - "model_architectures": "GPT2LMHeadModel" + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null }, { - "description": "ELYZA-japanese-CodeLlama-7b-instruct-gguf ELYZAさんが公開しているELYZA-japanese-CodeLlama-7b-instructのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/ELYZA-japanese-CodeLlama-7b-instruct-gguf", - "project_name": "ELYZA-japanese-CodeLlama-7b-instruct-gguf", - "downloads": 1730, + "description": "Model Description llava-calm2-siglip is an experimental Vision Language Model that can answer questions in Japanese about images.", + "url": "https://huggingface.co/cyberagent/llava-calm2-siglip", + "project_name": "llava-calm2-siglip", + "downloads": 1512, "source": "Hugging Face", - "score": -0.08726525039420419, - "first_commit": "2023-11-15 09:48:32", - "latest_commit": "2023-11-16 14:28:24", + "score": -0.07676031736532153, + "first_commit": "2024-06-12 19:35:20", + "latest_commit": "2024-06-12 19:40:39", "languages": [], "model_or_dataset": "model", - "model_size": 6.74, - "model_architectures": null + "model_size": 7.46, + "model_architectures": "LlavaForConditionalGeneration" }, { - "description": "OpenCALM-Large Model Description OpenCALM is a suite of decoder-only language models pre-trained on Japanese datasets, developed by", - "url": "https://huggingface.co/cyberagent/open-calm-large", - "project_name": "open-calm-large", - "downloads": 1726, + "description": "OpenCALM-3B Model Description OpenCALM is a suite of decoder-only language models pre-trained on Japanese datasets, developed by", + "url": "https://huggingface.co/cyberagent/open-calm-3b", + "project_name": "open-calm-3b", + "downloads": 1482, "source": "Hugging Face", - "score": -0.08732809582098106, - "first_commit": "2023-05-15 06:50:24", - "latest_commit": "2023-05-18 01:11:13", + "score": -0.07707846588141154, + "first_commit": "2023-05-15 07:14:36", + "latest_commit": "2023-05-18 01:11:50", "languages": [], "model_or_dataset": "model", "model_size": null, "model_architectures": "GPTNeoXForCausalLM" }, { - "description": "Corpus of Annual Reports in Japan", - "url": "https://github.com/chakki-works/CoARiJ", - "project_name": "CoARiJ", - "stargazers_count": 85, + "description": "A Python Module for JUMAN++/KNP", + "url": "https://github.com/ku-nlp/pyknp", + "project_name": "pyknp", + "stargazers_count": 88, "source": "GitHub", - "score": -0.08815702483635567, - "first_commit": "2019-09-02 14:12:48", - "latest_commit": "2020-12-19 14:00:34", + "score": -0.07739508672329466, + "first_commit": "2015-04-08 15:25:47", + "latest_commit": "2024-07-06 15:16:48", "languages": [ "Python" ], - "model_or_dataset": "dataset" + "model_or_dataset": null }, { - "description": "This dataset was created by automatically translating \"databricks-dolly-15k\" into Japanese.", - "url": "https://huggingface.co/datasets/kunishou/databricks-dolly-15k-ja", - "project_name": "databricks-dolly-15k-ja", - "downloads": 1655, - "source": "Hugging Face", - "score": -0.08844360214627046, - "first_commit": "2023-04-13 08:31:08", - "latest_commit": "2024-04-01 17:26:37", + "description": "STAIR captions: large-scale Japanese image caption dataset", + "url": "https://github.com/STAIR-Lab-CIT/STAIR-captions", + "project_name": "STAIR-captions", + "stargazers_count": 88, + "source": "GitHub", + "score": -0.07739508672329466, + "first_commit": "2017-02-21 16:49:14", + "latest_commit": "2018-07-04 18:24:35", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null + "model_or_dataset": "dataset" }, { - "description": "ELYZA-japanese-Llama-2-13b Model Description ELYZA-japanese-Llama-2-13b は、 Llama 2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。", - "url": "https://huggingface.co/elyza/ELYZA-japanese-Llama-2-13b", - "project_name": "ELYZA-japanese-Llama-2-13b", - "downloads": 1653, - "source": "Hugging Face", - "score": -0.0884750248596589, - "first_commit": "2023-12-25 16:38:08", - "latest_commit": "2023-12-27 01:40:43", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LlamaForCausalLM" + "description": "NMeCab: About Japanese morphological analyzer on .NET", + "url": "https://github.com/komutan/NMeCab", + "project_name": "NMeCab", + "stargazers_count": 88, + "source": "GitHub", + "score": -0.07739508672329466, + "first_commit": "2014-04-24 17:34:29", + "latest_commit": "2024-03-31 03:51:55", + "languages": [ + "C#" + ], + "model_or_dataset": "dataset" }, { - "description": "Japanese-StableLM-Base-Alpha-7B \"A parrot able to speak Japanese, ukiyoe, edo period\" — Stable Diffusion XL Model Description japanese-stablelm-base-alpha-7b is a 7B-parameter decoder-only language model pre-trained on a diverse collection of Japanese and English datasets which focus on maximizing Japanese language modeling performance and Japanese downstream task performance.", - "url": "https://huggingface.co/stabilityai/japanese-stablelm-base-alpha-7b", - "project_name": "japanese-stablelm-base-alpha-7b", - "downloads": 1637, + "description": "roberta-small-japanese-luw-upos Model Description", + "url": "https://huggingface.co/KoichiYasuoka/roberta-small-japanese-luw-upos", + "project_name": "roberta-small-japanese-luw-upos", + "downloads": 1435, "source": "Hugging Face", - "score": -0.08872640656676638, - "first_commit": "2023-08-09 14:30:09", - "latest_commit": "2023-08-22 09:36:29", + "score": -0.07757689855661923, + "first_commit": "2021-11-03 05:51:58", + "latest_commit": "2022-09-18 19:45:09", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "JapaneseStableLMAlphaForCausalLM" + "model_architectures": "RobertaForTokenClassification" }, { - "description": "upskyy/gte-korean-base This model is korsts and kornli finetuning model from Alibaba-NLP/gte-multilingual-base.", - "url": "https://huggingface.co/upskyy/gte-base-korean", - "project_name": "gte-base-korean", - "downloads": 1624, + "description": "japanese-gpt2-small This repository provides a small-sized Japanese GPT-2 model.", + "url": "https://huggingface.co/rinna/japanese-gpt2-small", + "project_name": "japanese-gpt2-small", + "downloads": 1432, "source": "Hugging Face", - "score": -0.08893065420379119, - "first_commit": "2024-08-08 14:34:44", - "latest_commit": "2024-08-08 15:29:27", + "score": -0.07760871340822824, + "first_commit": "2021-06-15 06:32:27", + "latest_commit": "2024-07-20 07:49:31", "languages": [], "model_or_dataset": "model", - "model_size": 0.305, - "model_architectures": "NewModel" + "model_size": 0.123, + "model_architectures": "GPT2LMHeadModel" }, { - "description": "Dataset Summary RealPersonaChat は，話者本人のペルソナと性格特性を含む，約14,000件の日本語雑談対話からなるコーパスです．", - "url": "https://huggingface.co/datasets/nu-dialogue/real-persona-chat", - "project_name": "real-persona-chat", - "downloads": 1624, + "description": "Ninja-v1-NSFW-128k-gguf Local-Novel-LLM-projectさんが公開しているNinja-v1-NSFW-128kのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Ninja-v1-NSFW-128k-gguf", + "project_name": "Ninja-v1-NSFW-128k-gguf", + "downloads": 1427, "source": "Hugging Face", - "score": -0.08893065420379119, - "first_commit": "2024-03-09 22:52:22", - "latest_commit": "2024-03-13 10:26:42", + "score": -0.0776617381609099, + "first_commit": "2024-05-01 17:45:52", + "latest_commit": "2024-05-04 13:25:47", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_or_dataset": "model", + "model_size": 7.24, "model_architectures": null }, { - "description": "luke-japanese-large-lite luke-japanese is the Japanese version of LUKE (Language Understanding with Knowledge-based Embeddings), a pre-trained knowledge-enhanced contextualized representation of words and entities.", - "url": "https://huggingface.co/studio-ousia/luke-japanese-large-lite", - "project_name": "luke-japanese-large-lite", - "downloads": 1612, + "description": "Phi-3-mini-128k-instruct-gguf microsoftさんが公開しているPhi-3-mini-128k-instructのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Phi-3-mini-128k-instruct-gguf", + "project_name": "Phi-3-mini-128k-instruct-gguf", + "downloads": 1409, "source": "Hugging Face", - "score": -0.0891191904841218, - "first_commit": "2022-11-07 14:26:40", - "latest_commit": "2022-11-09 11:19:36", + "score": -0.07785262727056391, + "first_commit": "2024-04-24 13:50:51", + "latest_commit": "2024-04-24 14:24:09", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LukeForMaskedLM" + "model_size": 3.82, + "model_architectures": null }, { - "description": "Llama-3-ELYZA-JP-8B-gguf elyzaさんが公開しているLlama-3-ELYZA-JP-8Bのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Llama-3-ELYZA-JP-8B-gguf", - "project_name": "Llama-3-ELYZA-JP-8B-gguf", - "downloads": 1607, + "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", + "url": "https://huggingface.co/tokyotech-llm/Swallow-7b-NVE-instruct-hf", + "project_name": "Swallow-7b-NVE-instruct-hf", + "downloads": 1375, "source": "Hugging Face", - "score": -0.08919774726759289, - "first_commit": "2024-06-26 16:36:04", - "latest_commit": "2024-06-26 17:55:35", + "score": -0.07821319558879926, + "first_commit": "2023-12-07 02:08:59", + "latest_commit": "2024-07-06 15:18:11", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": null + "model_size": 6.74, + "model_architectures": "LlamaForCausalLM" }, { - "description": "Japanese E5 Mixtral 7B Slerp GGUF GGUF conversion of oshizo/japanese-e5-mistral-7b_slerp Avaiable formats: Q2_K.gguf Q3_K.gguf Q4_K.gguf Q5_K.gguf", - "url": "https://huggingface.co/mm/japanese-e5-mistral-7b_slerp_gguf", - "project_name": "japanese-e5-mistral-7b_slerp_gguf", - "downloads": 1591, + "description": "Vecteus-v1-gguf Local-Novel-LLM-projectさんが公開しているVecteus-v1のggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Vecteus-v1-gguf", + "project_name": "Vecteus-v1-gguf", + "downloads": 1359, "source": "Hugging Face", - "score": -0.08944912897470036, - "first_commit": "2024-06-09 08:34:37", - "latest_commit": "2024-06-14 16:12:17", + "score": -0.07838287479738061, + "first_commit": "2024-05-01 17:49:42", + "latest_commit": "2024-05-01 18:37:01", "languages": [], "model_or_dataset": "model", "model_size": 7.24, "model_architectures": null }, { - "description": "OpenCALM-1B Model Description OpenCALM is a suite of decoder-only language models pre-trained on Japanese datasets, developed by", - "url": "https://huggingface.co/cyberagent/open-calm-1b", - "project_name": "open-calm-1b", - "downloads": 1585, + "description": "nlp-waseda/roberta-large-japanese-seq512 Model description This is a Japanese RoBERTa large model pretrained on Japanese Wikipedia and the Japanese portion of CC-100 with the maximum sequence length of 512.", + "url": "https://huggingface.co/nlp-waseda/roberta-large-japanese-seq512", + "project_name": "roberta-large-japanese-seq512", + "downloads": 1349, "source": "Hugging Face", - "score": -0.08954339711486567, - "first_commit": "2023-05-15 07:00:18", - "latest_commit": "2023-05-18 01:11:30", + "score": -0.07848892430274394, + "first_commit": "2022-06-13 09:46:45", + "latest_commit": "2022-10-21 14:49:40", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "GPTNeoXForCausalLM" + "model_architectures": "RobertaForMaskedLM" }, { - "description": "Llama-3-Swallow-8B-Instruct-v0.1-gguf tokyotech-llmさんが公開しているLlama-3-Swallow-8B-Instruct-v0.1のggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Llama-3-Swallow-8B-Instruct-v0.1-gguf", - "project_name": "Llama-3-Swallow-8B-Instruct-v0.1-gguf", - "downloads": 1569, + "description": "ELYZA-japanese-Llama-2-7b Model Description ELYZA-japanese-Llama-2-7b は、 Llama2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。 ", + "url": "https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b-fast", + "project_name": "ELYZA-japanese-Llama-2-7b-fast", + "downloads": 1335, "source": "Hugging Face", - "score": -0.08979477882197313, - "first_commit": "2024-07-01 16:42:54", - "latest_commit": "2024-07-02 10:43:55", + "score": -0.07863739361025261, + "first_commit": "2023-08-28 13:17:58", + "latest_commit": "2023-08-29 03:46:37", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": null + "model_size": null, + "model_architectures": "LlamaForCausalLM" }, { - "description": "Phi-3-mini-128k-instruct-gguf microsoftさんが公開しているPhi-3-mini-128k-instructのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Phi-3-mini-128k-instruct-gguf", - "project_name": "Phi-3-mini-128k-instruct-gguf", - "downloads": 1562, + "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", + "url": "https://huggingface.co/tokyotech-llm/Swallow-7b-NVE-hf", + "project_name": "Swallow-7b-NVE-hf", + "downloads": 1307, "source": "Hugging Face", - "score": -0.08990475831883266, - "first_commit": "2024-04-24 13:50:51", - "latest_commit": "2024-04-24 14:24:09", + "score": -0.07893433222526997, + "first_commit": "2023-11-30 09:02:26", + "latest_commit": "2024-06-29 08:56:18", "languages": [], "model_or_dataset": "model", - "model_size": 3.82, - "model_architectures": null + "model_size": null, + "model_architectures": "LlamaForCausalLM" }, { - "description": "OpenCALM-3B Model Description OpenCALM is a suite of decoder-only language models pre-trained on Japanese datasets, developed by", - "url": "https://huggingface.co/cyberagent/open-calm-3b", - "project_name": "open-calm-3b", - "downloads": 1520, + "description": "Japanese-StableLM-Instruct-Beta-70B A cute robot wearing a kimono writes calligraphy with one single brush — Stable Diffusion XL Model Description japanese-stablelm-instruct-beta-70b is a 70B-parameter decoder-only language model based on japanese-stablelm-base-beta-70b and further fine tuned on Databricks Dolly-15k, Anthropic HH, and other public data.", + "url": "https://huggingface.co/stabilityai/japanese-stablelm-instruct-beta-70b", + "project_name": "japanese-stablelm-instruct-beta-70b", + "downloads": 1304, "source": "Hugging Face", - "score": -0.09056463529998977, - "first_commit": "2023-05-15 07:14:36", - "latest_commit": "2023-05-18 01:11:50", + "score": -0.07896614707687896, + "first_commit": "2023-10-30 07:47:31", + "latest_commit": "2023-12-19 06:45:10", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "GPTNeoXForCausalLM" + "model_size": 69.0, + "model_architectures": "LlamaForCausalLM" }, { - "description": "このツールは、複数のデータセットを横断して日本語の大規模言語モデルを自動評価するものです．", - "url": "https://github.com/llm-jp/llm-jp-eval", - "project_name": "llm-jp-eval", - "stargazers_count": 84, - "source": "GitHub", - "score": -0.09108856684895345, - "first_commit": "2023-10-19 19:36:10", - "latest_commit": "2024-07-18 21:31:53", - "languages": [ - "Python" - ], - "model_or_dataset": null - }, - { - "description": "japanese-gpt2-small This repository provides a small-sized Japanese GPT-2 model.", - "url": "https://huggingface.co/rinna/japanese-gpt2-small", - "project_name": "japanese-gpt2-small", - "downloads": 1478, - "source": "Hugging Face", - "score": -0.09122451228114689, - "first_commit": "2021-06-15 06:32:27", - "latest_commit": "2024-07-20 07:49:31", - "languages": [], - "model_or_dataset": "model", - "model_size": 0.123, - "model_architectures": "GPT2LMHeadModel" - }, - { - "description": "Wav2Vec2-Large-Japanese Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using the Common Voice, JSUT, TEDxJP and some other data.", - "url": "https://huggingface.co/NTQAI/wav2vec2-large-japanese", - "project_name": "wav2vec2-large-japanese", - "downloads": 1477, + "description": "gpt-neox-japanese-2.7b", + "url": "https://huggingface.co/abeja/gpt-neox-japanese-2.7b", + "project_name": "gpt-neox-japanese-2.7b", + "downloads": 1300, "source": "Hugging Face", - "score": -0.09124022363784111, - "first_commit": "2021-07-05 02:44:40", - "latest_commit": "2023-02-17 13:07:47", + "score": -0.0790085668790243, + "first_commit": "2022-08-29 02:15:44", + "latest_commit": "2023-04-10 05:12:30", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "Wav2Vec2ForCTC" + "model_architectures": "GPTNeoXJapaneseForCausalLM" }, { - "description": "ELYZA-japanese-Llama-2-13b-fast-instruct Model Description ELYZA-japanese-Llama-2-13b は、 Llama 2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。 ", - "url": "https://huggingface.co/elyza/ELYZA-japanese-Llama-2-13b-fast-instruct", - "project_name": "ELYZA-japanese-Llama-2-13b-fast-instruct", - "downloads": 1475, + "description": "Japanese-StableLM-Base-Beta-70B A cute robot wearing a kimono writes calligraphy with one single brush — Stable Diffusion XL Model Description japanese-stablelm-base-beta-70b is a 70B-parameter decoder-only language model based on Llama-2-70b that has been fine-tuned on a diverse collection of Japanese data, with the intent of maximizing downstream performance on Japanese language tasks.", + "url": "https://huggingface.co/stabilityai/japanese-stablelm-base-beta-70b", + "project_name": "japanese-stablelm-base-beta-70b", + "downloads": 1291, "source": "Hugging Face", - "score": -0.09127164635122954, - "first_commit": "2023-12-25 18:14:10", - "latest_commit": "2023-12-27 01:41:51", + "score": -0.0791040114338513, + "first_commit": "2023-10-30 07:46:28", + "latest_commit": "2023-12-19 06:44:53", "languages": [], "model_or_dataset": "model", - "model_size": null, + "model_size": 69.0, "model_architectures": "LlamaForCausalLM" }, { - "description": "bilingual-gpt-neox-4b Overview This repository provides an English-Japanese bilingual GPT-NeoX model of 3.8 billion parameters.", - "url": "https://huggingface.co/rinna/bilingual-gpt-neox-4b", - "project_name": "bilingual-gpt-neox-4b", - "downloads": 1473, + "description": "BERT Base Japanese for Irony", + "url": "https://huggingface.co/kit-nlp/bert-base-japanese-sentiment-irony", + "project_name": "bert-base-japanese-sentiment-irony", + "downloads": 1278, "source": "Hugging Face", - "score": -0.09130306906461798, - "first_commit": "2023-07-31 02:34:03", - "latest_commit": "2024-07-20 08:02:07", + "score": -0.07924187579082365, + "first_commit": "2022-11-07 06:29:21", + "latest_commit": "2022-11-08 04:23:27", "languages": [], "model_or_dataset": "model", - "model_size": 3.95, - "model_architectures": "GPTNeoXForCausalLM" + "model_size": null, + "model_architectures": "BertForSequenceClassification" }, { - "description": "calm3-22b-RP-GGUF 概要 Aratako/calm3-22b-RPの量子化済みGGUF版です。", - "url": "https://huggingface.co/Aratako/calm3-22b-RP-GGUF", - "project_name": "calm3-22b-RP-GGUF", - "downloads": 1463, + "description": "ELYZA-japanese-Llama-2-7b-instruct-gguf ELYZAさんが公開しているELYZA-japanese-Llama-2-7b-instructのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-7b-instruct-gguf", + "project_name": "ELYZA-japanese-Llama-2-7b-instruct-gguf", + "downloads": 1260, "source": "Hugging Face", - "score": -0.09146018263156015, - "first_commit": "2024-08-21 01:13:32", - "latest_commit": "2024-08-21 13:26:35", + "score": -0.07943276490047765, + "first_commit": "2023-08-29 05:33:45", + "latest_commit": "2023-11-16 14:27:23", "languages": [], "model_or_dataset": "model", - "model_size": 22.5, + "model_size": 6.74, "model_architectures": null }, { - "description": "This dataset contains a diverse set of natural Japanese speech, collected from terrestrial television streams.", - "url": "https://huggingface.co/datasets/reazon-research/reazonspeech", - "project_name": "reazonspeech", - "downloads": 1454, + "description": "Dataset Summary RealPersonaChat は，話者本人のペルソナと性格特性を含む，約14,000件の日本語雑談対話からなるコーパスです．", + "url": "https://huggingface.co/datasets/nu-dialogue/real-persona-chat", + "project_name": "real-persona-chat", + "downloads": 1220, "source": "Hugging Face", - "score": -0.09160158484180811, - "first_commit": null, - "latest_commit": null, + "score": -0.07985696292193101, + "first_commit": "2024-03-09 22:52:22", + "latest_commit": "2024-03-13 10:26:42", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "Model Card for Japanese character-level DeBERTa V2 base Model description This is a Japanese DeBERTa V2 base model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.", - "url": "https://huggingface.co/ku-nlp/deberta-v2-base-japanese-char-wwm", - "project_name": "deberta-v2-base-japanese-char-wwm", - "downloads": 1452, + "description": "japanese-large-lm-3.6b-instruction-sft", + "url": "https://huggingface.co/line-corporation/japanese-large-lm-3.6b-instruction-sft", + "project_name": "japanese-large-lm-3.6b-instruction-sft", + "downloads": 1205, "source": "Hugging Face", - "score": -0.09163300755519654, - "first_commit": "2023-01-18 13:55:30", - "latest_commit": "2023-03-26 03:32:27", + "score": -0.08001603717997602, + "first_commit": "2023-08-14 17:18:09", + "latest_commit": "2023-08-24 10:08:28", "languages": [], "model_or_dataset": "model", - "model_size": 0.122, - "model_architectures": "DebertaV2ForMaskedLM" + "model_size": 3.68, + "model_architectures": "GPTNeoXForCausalLM" }, { - "description": "alabnii/jmedroberta-base-sentencepiece Model description This is a Japanese RoBERTa base model pre-trained on academic articles in medical sciences collected by Japan Science and Technology Agency (JST).", - "url": "https://huggingface.co/alabnii/jmedroberta-base-sentencepiece", - "project_name": "jmedroberta-base-sentencepiece", - "downloads": 1451, + "description": "rinna/nekomata-7b Overview We conduct continual pre-training of qwen-7b on 30B tokens from a mixture of Japanese and English datasets.", + "url": "https://huggingface.co/rinna/nekomata-7b", + "project_name": "nekomata-7b", + "downloads": 1198, "source": "Hugging Face", - "score": -0.09164871891189075, - "first_commit": "2022-12-22 17:20:33", - "latest_commit": "2023-03-21 23:57:37", + "score": -0.08009027183373035, + "first_commit": "2023-12-19 06:58:44", + "latest_commit": "2024-07-20 08:35:21", "languages": [], "model_or_dataset": "model", - "model_size": 0.109, - "model_architectures": "BertForMaskedLM" + "model_size": 7.72, + "model_architectures": "QWenLMHeadModel" }, { - "description": "Model Card for Japanese DeBERTa V2 tiny Model description", - "url": "https://huggingface.co/ku-nlp/deberta-v2-tiny-japanese", - "project_name": "deberta-v2-tiny-japanese", - "downloads": 1442, + "description": "Places in japan.", + "url": "https://huggingface.co/datasets/JapanDegitalMaterial/Places_in_Japan", + "project_name": "Places_in_Japan", + "downloads": 1186, "source": "Hugging Face", - "score": -0.0917901211221387, - "first_commit": "2023-01-18 13:36:09", - "latest_commit": "2023-03-23 16:13:46", + "score": -0.08021753124016637, + "first_commit": "2023-09-23 12:35:06", + "latest_commit": "2023-09-23 14:00:16", "languages": [], - "model_or_dataset": "model", - "model_size": 0.013900000000000001, - "model_architectures": "DebertaV2ForMaskedLM" + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null }, { - "description": "Ninja-v1-NSFW-128k-gguf Local-Novel-LLM-projectさんが公開しているNinja-v1-NSFW-128kのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Ninja-v1-NSFW-128k-gguf", - "project_name": "Ninja-v1-NSFW-128k-gguf", - "downloads": 1431, + "description": "In this study, we introduce a new dataset, WRIME, for emotional intensity estimation.", + "url": "https://huggingface.co/datasets/shunk031/wrime", + "project_name": "wrime", + "downloads": 1184, "source": "Hugging Face", - "score": -0.0919629460457751, - "first_commit": "2024-05-01 17:45:52", - "latest_commit": "2024-05-04 13:25:47", + "score": -0.08023874114123904, + "first_commit": "2023-01-12 10:43:54", + "latest_commit": "2023-01-15 12:39:01", "languages": [], - "model_or_dataset": "model", - "model_size": 7.24, + "model_or_dataset": "dataset", + "model_size": null, "model_architectures": null }, { - "description": "roberta-small-japanese-luw-upos Model Description", - "url": "https://huggingface.co/KoichiYasuoka/roberta-small-japanese-luw-upos", - "project_name": "roberta-small-japanese-luw-upos", - "downloads": 1431, + "description": "alpacaデータセットを日本語化したものです", + "url": "https://github.com/shi3z/alpaca_ja", + "project_name": "alpaca_ja", + "stargazers_count": 87, + "source": "GitHub", + "score": -0.08033510728456436, + "first_commit": "2023-04-01 07:03:33", + "latest_commit": "2023-05-17 15:43:50", + "languages": [], + "model_or_dataset": "dataset" + }, + { + "description": "Please feel free to open an issue or pull request. ", + "url": "https://huggingface.co/datasets/kumapo/JAQKET", + "project_name": "JAQKET", + "downloads": 1154, "source": "Hugging Face", - "score": -0.0919629460457751, - "first_commit": "2021-11-03 05:51:58", - "latest_commit": "2022-09-18 19:45:09", + "score": -0.08055688965732904, + "first_commit": "2023-06-21 13:04:38", + "latest_commit": "2023-10-09 06:44:28", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "RobertaForTokenClassification" + "model_architectures": null }, { - "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", - "url": "https://huggingface.co/tokyotech-llm/Swallow-7b-NVE-instruct-hf", - "project_name": "Swallow-7b-NVE-instruct-hf", - "downloads": 1401, + "description": "hotchpotch/japanese-reranker-cross-encoder-large-v1 日本語で学習させた Reranker (CrossEncoder) シ��ーズです。 ", + "url": "https://huggingface.co/hotchpotch/japanese-reranker-cross-encoder-large-v1", + "project_name": "japanese-reranker-cross-encoder-large-v1", + "downloads": 1120, "source": "Hugging Face", - "score": -0.0924342867466016, - "first_commit": "2023-12-07 02:08:59", - "latest_commit": "2024-07-06 15:18:11", + "score": -0.08091745797556439, + "first_commit": "2024-03-28 20:53:30", + "latest_commit": "2024-04-01 02:39:45", "languages": [], "model_or_dataset": "model", - "model_size": 6.74, - "model_architectures": "LlamaForCausalLM" + "model_size": 0.337, + "model_architectures": "BertForSequenceClassification" }, { - "description": "recruit-jp/japanese-clip-vit-b-32-roberta-base Overview Developed by: Recruit Co.", - "url": "https://huggingface.co/recruit-jp/japanese-clip-vit-b-32-roberta-base", - "project_name": "japanese-clip-vit-b-32-roberta-base", - "downloads": 1396, + "description": "Japanese-LLaMA-3-8B Japanese-LLaMA-3-8Bは基盤モデル、フルモデルです。 ", + "url": "https://huggingface.co/owner203/japanese-llama-3-8b", + "project_name": "japanese-llama-3-8b", + "downloads": 1109, "source": "Hugging Face", - "score": -0.09251284353007269, - "first_commit": "2023-12-20 06:06:12", - "latest_commit": "2024-01-22 07:41:59", + "score": -0.08103411243146406, + "first_commit": "2024-06-05 02:19:05", + "latest_commit": "2024-06-21 06:35:41", "languages": [], "model_or_dataset": "model", - "model_size": 0.198, - "model_architectures": "JapaneseCLIPModel" + "model_size": 8.03, + "model_architectures": "LlamaForCausalLM" }, { - "description": "ELYZA-japanese-Llama-2-7b-instruct-gguf ELYZAさんが公開しているELYZA-japanese-Llama-2-7b-instructのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-7b-instruct-gguf", - "project_name": "ELYZA-japanese-Llama-2-7b-instruct-gguf", - "downloads": 1364, + "description": "Llama-3-ELYZA-JP-8B-gguf elyzaさんが公開しているLlama-3-ELYZA-JP-8Bのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Llama-3-ELYZA-JP-8B-gguf", + "project_name": "Llama-3-ELYZA-JP-8B-gguf", + "downloads": 1096, "source": "Hugging Face", - "score": -0.09301560694428763, - "first_commit": "2023-08-29 05:33:45", - "latest_commit": "2023-11-16 14:27:23", + "score": -0.0811719767884364, + "first_commit": "2024-06-26 16:36:04", + "latest_commit": "2024-06-26 17:55:35", "languages": [], "model_or_dataset": "model", - "model_size": 6.74, + "model_size": 8.03, "model_architectures": null }, { - "description": "ELYZA-japanese-Llama-2-7b Model Description ELYZA-japanese-Llama-2-7b は、 Llama2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。 ", - "url": "https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b-fast", - "project_name": "ELYZA-japanese-Llama-2-7b-fast", - "downloads": 1363, + "description": "Ninja-v1-NSFW-gguf Local-Novel-LLM-projectさんが公開しているNinja-v1-NSFWのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Ninja-v1-NSFW-gguf", + "project_name": "Ninja-v1-NSFW-gguf", + "downloads": 1093, "source": "Hugging Face", - "score": -0.09303131830098185, - "first_commit": "2023-08-28 13:17:58", - "latest_commit": "2023-08-29 03:46:37", + "score": -0.08120379164004542, + "first_commit": "2024-05-03 14:03:23", + "latest_commit": "2024-05-04 13:26:52", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LlamaForCausalLM" + "model_size": 7.24, + "model_architectures": null }, { - "description": "Japanese-StableLM-Instruct-Beta-70B A cute robot wearing a kimono writes calligraphy with one single brush — Stable Diffusion XL Model Description japanese-stablelm-instruct-beta-70b is a 70B-parameter decoder-only language model based on japanese-stablelm-base-beta-70b and further fine tuned on Databricks Dolly-15k, Anthropic HH, and other public data.", - "url": "https://huggingface.co/stabilityai/japanese-stablelm-instruct-beta-70b", - "project_name": "japanese-stablelm-instruct-beta-70b", - "downloads": 1341, + "description": "HODACHI-Borea-Phi-3.5-mini-Instruct-Jp-gguf HODACHIさんが公開しているBorea-Phi-3.5-mini-Instruct-Jpのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/HODACHI-Borea-Phi-3.5-mini-Instruct-Jp-gguf", + "project_name": "HODACHI-Borea-Phi-3.5-mini-Instruct-Jp-gguf", + "downloads": 1083, "source": "Hugging Face", - "score": -0.09337696814825464, - "first_commit": "2023-10-30 07:47:31", - "latest_commit": "2023-12-19 06:45:10", + "score": -0.08130984114540875, + "first_commit": "2024-08-21 09:58:41", + "latest_commit": "2024-08-21 11:08:38", "languages": [], "model_or_dataset": "model", - "model_size": 69.0, - "model_architectures": "LlamaForCausalLM" + "model_size": 3.82, + "model_architectures": null }, { "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", "url": "https://huggingface.co/tokyotech-llm/Swallow-13b-instruct-v0.1", "project_name": "Swallow-13b-instruct-v0.1", - "downloads": 1335, + "downloads": 1082, "source": "Hugging Face", - "score": -0.09347123628841994, + "score": -0.08132044609594509, "first_commit": "2024-03-04 11:30:28", "latest_commit": "2024-06-29 09:00:15", "languages": [], @@ -4391,262 +4503,236 @@ "model_architectures": "LlamaForCausalLM" }, { - "description": "Japanese-StableLM-Base-Beta-70B A cute robot wearing a kimono writes calligraphy with one single brush — Stable Diffusion XL Model Description japanese-stablelm-base-beta-70b is a 70B-parameter decoder-only language model based on Llama-2-70b that has been fine-tuned on a diverse collection of Japanese data, with the intent of maximizing downstream performance on Japanese language tasks.", - "url": "https://huggingface.co/stabilityai/japanese-stablelm-base-beta-70b", - "project_name": "japanese-stablelm-base-beta-70b", - "downloads": 1310, + "description": "Wav2Vec2-Large-Japanese Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using the Common Voice, JSUT, TEDxJP and some other data.", + "url": "https://huggingface.co/NTQAI/wav2vec2-large-japanese", + "project_name": "wav2vec2-large-japanese", + "downloads": 1075, "source": "Hugging Face", - "score": -0.09386402020577536, - "first_commit": "2023-10-30 07:46:28", - "latest_commit": "2023-12-19 06:44:53", + "score": -0.08139468074969942, + "first_commit": "2021-07-05 02:44:40", + "latest_commit": "2023-02-17 13:07:47", "languages": [], "model_or_dataset": "model", - "model_size": 69.0, - "model_architectures": "LlamaForCausalLM" + "model_size": null, + "model_architectures": "Wav2Vec2ForCTC" }, { - "description": "llm-lora-classification", - "url": "https://github.com/hppRC/llm-lora-classification", - "project_name": "llm-lora-classification", - "stargazers_count": 83, - "source": "GitHub", - "score": -0.09402010886155124, - "first_commit": "2023-07-17 12:42:57", - "latest_commit": "2023-07-22 19:46:45", - "languages": [ - "Python" - ], - "model_or_dataset": null - }, - { - "description": "Word2vec (word to vectors) approach for Japanese language using Gensim and Mecab.", - "url": "https://github.com/philipperemy/japanese-words-to-vectors", - "project_name": "japanese-words-to-vectors", - "stargazers_count": 83, - "source": "GitHub", - "score": -0.09402010886155124, - "first_commit": "2016-09-04 09:43:00", - "latest_commit": "2020-08-09 19:48:23", - "languages": [ - "Python" - ], - "model_or_dataset": "model" - }, - { - "description": "Vecteus-v1-gguf Local-Novel-LLM-projectさんが公開しているVecteus-v1のggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Vecteus-v1-gguf", - "project_name": "Vecteus-v1-gguf", - "downloads": 1289, + "description": "ELYZA-japanese-Llama-2-13b-fast Model Description ELYZA-japanese-Llama-2-13b は、 Llama 2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。 ", + "url": "https://huggingface.co/elyza/ELYZA-japanese-Llama-2-13b-fast", + "project_name": "ELYZA-japanese-Llama-2-13b-fast", + "downloads": 1073, "source": "Hugging Face", - "score": -0.09419395869635393, - "first_commit": "2024-05-01 17:49:42", - "latest_commit": "2024-05-01 18:37:01", + "score": -0.0814158906507721, + "first_commit": "2023-12-25 17:14:45", + "latest_commit": "2023-12-27 01:41:31", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": null + "model_size": null, + "model_architectures": "LlamaForCausalLM" }, { - "description": "rinna/japanese-wav2vec2-base Overview This is a Japanese wav2vec 2.0 Base model trained by rinna Co.", - "url": "https://huggingface.co/rinna/japanese-wav2vec2-base", - "project_name": "japanese-wav2vec2-base", - "downloads": 1272, + "description": "Llama-3.1-70B-Instruct-gguf meta-llamaさんが公開しているMeta-Llama-3.1-70B-Instructのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Llama-3.1-70B-Instruct-gguf", + "project_name": "Llama-3.1-70B-Instruct-gguf", + "downloads": 1044, "source": "Hugging Face", - "score": -0.09446105176015561, - "first_commit": "2024-03-06 01:07:56", - "latest_commit": "2024-07-22 08:11:46", + "score": -0.08172343421632577, + "first_commit": "2024-07-23 17:25:23", + "latest_commit": "2024-07-24 21:04:27", "languages": [], "model_or_dataset": "model", - "model_size": 0.095, - "model_architectures": "Wav2Vec2ForPreTraining" + "model_size": 70.6, + "model_architectures": null }, { - "description": "Model Description llava-calm2-siglip is an experimental Vision Language Model that can answer questions in Japanese about images.", - "url": "https://huggingface.co/cyberagent/llava-calm2-siglip", - "project_name": "llava-calm2-siglip", - "downloads": 1271, + "description": "GitHub リポジトリ ids-cv/wrime で公開されているデータセットを利用しています。 ", + "url": "https://huggingface.co/datasets/llm-book/wrime-sentiment", + "project_name": "wrime-sentiment", + "downloads": 1039, "source": "Hugging Face", - "score": -0.09447676311684983, - "first_commit": "2024-06-12 19:35:20", - "latest_commit": "2024-06-12 19:40:39", + "score": -0.08177645896900744, + "first_commit": "2023-07-29 06:38:26", + "latest_commit": "2023-10-06 00:56:38", "languages": [], - "model_or_dataset": "model", - "model_size": 7.46, - "model_architectures": "LlavaForConditionalGeneration" + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null }, { - "description": "nlp-waseda/roberta-base-japanese Model description This is a Japanese RoBERTa base model pretrained on Japanese Wikipedia and the Japanese portion of CC-100.", - "url": "https://huggingface.co/nlp-waseda/roberta-base-japanese", - "project_name": "roberta-base-japanese", - "downloads": 1206, + "description": "読み込み方 from datasets import load_dataset dataset = load_dataset(\"YANS-official/ogiri-debug\", split=\"test\") 概要 大喜利生成の動作確認用データセットです。", + "url": "https://huggingface.co/datasets/YANS-official/ogiri-debug", + "project_name": "ogiri-debug", + "downloads": 1038, "source": "Hugging Face", - "score": -0.09549800130197394, - "first_commit": "2021-12-20 05:12:06", - "latest_commit": "2022-10-21 14:46:36", + "score": -0.08178706391954377, + "first_commit": "2024-08-30 04:18:35", + "latest_commit": "2024-08-30 14:52:03", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "RobertaForMaskedLM" + "model_architectures": null }, { - "description": "ELYZA-japanese-Llama-2-13b-fast-instruct-gguf ELYZAさんが公開しているELYZA-japanese-Llama-2-13b-fast-instructのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-13b-fast-instruct-gguf", - "project_name": "ELYZA-japanese-Llama-2-13b-fast-instruct-gguf", - "downloads": 1170, + "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", + "url": "https://huggingface.co/tokyotech-llm/Swallow-7b-plus-hf", + "project_name": "Swallow-7b-plus-hf", + "downloads": 1022, "source": "Hugging Face", - "score": -0.09606361014296576, - "first_commit": "2023-12-27 09:46:04", - "latest_commit": "2023-12-27 11:39:18", + "score": -0.08195674312812512, + "first_commit": "2024-02-29 11:28:52", + "latest_commit": "2024-06-29 08:56:19", "languages": [], "model_or_dataset": "model", - "model_size": 13.1, - "model_architectures": null + "model_size": null, + "model_architectures": "LlamaForCausalLM" }, { - "description": "rinna/nekomata-7b Overview We conduct continual pre-training of qwen-7b on 30B tokens from a mixture of Japanese and English datasets.", - "url": "https://huggingface.co/rinna/nekomata-7b", - "project_name": "nekomata-7b", - "downloads": 1155, + "description": "japanese-gpt-neox-3.6b-instruction-sft Overview This repository provides a Japanese GPT-NeoX model of 3.6 billion parameters.", + "url": "https://huggingface.co/rinna/japanese-gpt-neox-3.6b-instruction-sft", + "project_name": "japanese-gpt-neox-3.6b-instruction-sft", + "downloads": 1017, "source": "Hugging Face", - "score": -0.09629928049337902, - "first_commit": "2023-12-19 06:58:44", - "latest_commit": "2024-07-20 08:35:21", + "score": -0.08200976788080679, + "first_commit": "2023-05-17 02:16:28", + "latest_commit": "2024-07-20 07:56:34", "languages": [], "model_or_dataset": "model", - "model_size": 7.72, - "model_architectures": "QWenLMHeadModel" + "model_size": 3.76, + "model_architectures": "GPTNeoXForCausalLM" }, { - "description": "In this study, we introduce a new dataset, WRIME, for emotional intensity estimation.", - "url": "https://huggingface.co/datasets/shunk031/wrime", - "project_name": "wrime", - "downloads": 1146, + "description": "読み込み方 from datasets import load_dataset dataset = load_dataset(\"YANS-official/senryu-debug\", split=\"test\") 概要 大喜利生成の動作確認用データセットです。", + "url": "https://huggingface.co/datasets/YANS-official/senryu-debug", + "project_name": "senryu-debug", + "downloads": 1017, "source": "Hugging Face", - "score": -0.09644068270362696, - "first_commit": "2023-01-12 10:43:54", - "latest_commit": "2023-01-15 12:39:01", + "score": -0.08200976788080679, + "first_commit": "2024-08-30 05:47:58", + "latest_commit": "2024-09-04 10:49:15", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "HODACHI-EZO-Humanities-9B-gemma-2-it-gguf HODACHIさんが公開しているEZO-Humanities-9B-gemma-2-itのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/HODACHI-EZO-Humanities-9B-gemma-2-it-gguf", - "project_name": "HODACHI-EZO-Humanities-9B-gemma-2-it-gguf", - "downloads": 1143, + "description": "PLaMo-13B-Instruct Model Description PLaMo-13B-Instruct is an instruct fine-tuned model built upon the 8192 context length version of PLaMo-13B text generation model.", + "url": "https://huggingface.co/pfnet/plamo-13b-instruct", + "project_name": "plamo-13b-instruct", + "downloads": 987, "source": "Hugging Face", - "score": -0.09648781677370961, - "first_commit": "2024-07-15 15:43:00", - "latest_commit": "2024-07-15 17:01:09", + "score": -0.0823279163968968, + "first_commit": "2023-10-26 02:11:24", + "latest_commit": "2024-01-25 07:46:09", "languages": [], "model_or_dataset": "model", - "model_size": 9.24, - "model_architectures": null + "model_size": 13.1, + "model_architectures": "PlamoForCausalLM" }, { - "description": "hotchpotch/japanese-reranker-cross-encoder-large-v1 日本語で学習させた Reranker (CrossEncoder) シリーズです。 ", - "url": "https://huggingface.co/hotchpotch/japanese-reranker-cross-encoder-large-v1", - "project_name": "japanese-reranker-cross-encoder-large-v1", - "downloads": 1117, + "description": "hotchpotch/japanese-reranker-cross-encoder-base-v1 日本語で学習させた Reranker (CrossEncoder) シリーズです。 ", + "url": "https://huggingface.co/hotchpotch/japanese-reranker-cross-encoder-base-v1", + "project_name": "japanese-reranker-cross-encoder-base-v1", + "downloads": 980, "source": "Hugging Face", - "score": -0.09689631204775927, - "first_commit": "2024-03-28 20:53:30", - "latest_commit": "2024-04-01 02:39:45", + "score": -0.08240215105065114, + "first_commit": "2024-03-29 07:07:38", + "latest_commit": "2024-04-01 02:39:31", "languages": [], "model_or_dataset": "model", - "model_size": 0.337, + "model_size": 0.111, "model_architectures": "BertForSequenceClassification" }, { - "description": "External dictionary importer for Yomichan.", - "url": "https://github.com/FooSoft/yomichan-import", - "project_name": "yomichan-import", - "stargazers_count": 82, - "source": "GitHub", - "score": -0.09695165087414902, - "first_commit": "2016-07-26 20:24:33", - "latest_commit": "2023-02-25 12:43:03", - "languages": [ - "Go" - ], - "model_or_dataset": null + "description": "Tanuki-8x8B-dpo-v1.0 モデルについて Tanuki-8x8Bは、フルスクラッチで約1.7Tトークン事前学習を行った8x8Bパラメータ（総パラメータ約47B、アクティブパラメータ約13B）の大規模言語モデルです。", + "url": "https://huggingface.co/weblab-GENIAC/Tanuki-8x8B-dpo-v1.0", + "project_name": "Tanuki-8x8B-dpo-v1.0", + "downloads": 973, + "source": "Hugging Face", + "score": -0.08247638570440548, + "first_commit": "2024-08-12 12:47:11", + "latest_commit": "2024-09-02 23:47:09", + "languages": [], + "model_or_dataset": "model", + "model_size": 47.0, + "model_architectures": "TanukiForCausalLM" }, { - "description": "日英変換・英語略語展開のための IME 追加辞書 orange_book 日本語から英語への和英変換や英語略語の展開を Google 日本語入力や ATOK などで可能にする IME 拡張辞書", - "url": "https://github.com/peaceiris/google-ime-dictionary", - "project_name": "google-ime-dictionary", - "stargazers_count": 82, - "source": "GitHub", - "score": -0.09695165087414902, - "first_commit": "2018-09-13 01:54:32", - "latest_commit": "2023-01-16 10:47:31", + "description": "Model Card for Japanese BART base Model description This is a Japanese BART base model pre-trained on Japanese Wikipedia.", + "url": "https://huggingface.co/ku-nlp/bart-base-japanese", + "project_name": "bart-base-japanese", + "downloads": 973, + "source": "Hugging Face", + "score": -0.08247638570440548, + "first_commit": "2023-05-09 07:00:51", + "latest_commit": "2023-05-12 11:03:20", "languages": [], - "model_or_dataset": "dataset" + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "MBartForConditionalGeneration" }, { - "description": "GitHub リポジトリ ids-cv/wrime で公開されているデータセットを利用しています。 ", - "url": "https://huggingface.co/datasets/llm-book/wrime-sentiment", - "project_name": "wrime-sentiment", - "downloads": 1103, + "description": "OpenCALM-Medium Model Description OpenCALM is a suite of decoder-only language models pre-trained on Japanese datasets, developed by", + "url": "https://huggingface.co/cyberagent/open-calm-medium", + "project_name": "open-calm-medium", + "downloads": 969, "source": "Hugging Face", - "score": -0.0971162710414783, - "first_commit": "2023-07-29 06:38:26", - "latest_commit": "2023-10-06 00:56:38", + "score": -0.08251880550655082, + "first_commit": "2023-05-15 06:44:47", + "latest_commit": "2023-05-18 01:10:54", "languages": [], - "model_or_dataset": "dataset", + "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "GPTNeoXForCausalLM" }, { - "description": "llm-jp-13b-instruct-full-dolly_en-dolly_ja-ichikara_003_001-oasst_en-oasst_ja-v1.1", - "url": "https://huggingface.co/llm-jp/llm-jp-13b-instruct-full-dolly_en-dolly_ja-ichikara_003_001-oasst_en-oasst_ja-v1.1", - "project_name": "llm-jp-13b-instruct-full-dolly_en-dolly_ja-ichikara_003_001-oasst_en-oasst_ja-v1.1", - "downloads": 1084, + "description": "japanese-large-lm-1.7b This repository provides a 1.7B parameters Japanese language model, trained by LINE Corporation.", + "url": "https://huggingface.co/line-corporation/japanese-large-lm-1.7b", + "project_name": "japanese-large-lm-1.7b", + "downloads": 961, "source": "Hugging Face", - "score": -0.09741478681866843, - "first_commit": "2024-01-29 12:52:31", - "latest_commit": "2024-02-07 19:49:25", + "score": -0.08260364511084148, + "first_commit": "2023-07-21 00:46:33", + "latest_commit": "2023-08-17 01:06:37", "languages": [], "model_or_dataset": "model", - "model_size": 12.9, + "model_size": 1.75, "model_architectures": "GPT2LMHeadModel" }, { - "description": "Chatbot Arena Conversationsの質問文から、aixsatoshi/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct-v2を使用して応答文を作成しました 質問文は、以下のモデルのPrompt部分を使用しました Chatbot Arena Conversations JA (calm2) 以下引用です。 ", - "url": "https://huggingface.co/datasets/aixsatoshi/Swallow-MX-chatbot-DPO", - "project_name": "Swallow-MX-chatbot-DPO", - "downloads": 1078, + "description": "nlp-waseda/roberta-base-japanese Model description This is a Japanese RoBERTa base model pretrained on Japanese Wikipedia and the Japanese portion of CC-100.", + "url": "https://huggingface.co/nlp-waseda/roberta-base-japanese", + "project_name": "roberta-base-japanese", + "downloads": 956, "source": "Hugging Face", - "score": -0.09750905495883373, - "first_commit": "2024-03-31 06:42:39", - "latest_commit": "2024-03-31 08:16:43", + "score": -0.08265666986352314, + "first_commit": "2021-12-20 05:12:06", + "latest_commit": "2022-10-21 14:46:36", "languages": [], - "model_or_dataset": "dataset", + "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "RobertaForMaskedLM" }, { - "description": "ELYZA-japanese-Llama-2-13b-fast Model Description ELYZA-japanese-Llama-2-13b は、 Llama 2をベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。 ", - "url": "https://huggingface.co/elyza/ELYZA-japanese-Llama-2-13b-fast", - "project_name": "ELYZA-japanese-Llama-2-13b-fast", - "downloads": 1077, + "description": "ELYZA-japanese-Llama-2-13b-fast-instruct-gguf ELYZAさんが公開しているELYZA-japanese-Llama-2-13b-fast-instructのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-13b-fast-instruct-gguf", + "project_name": "ELYZA-japanese-Llama-2-13b-fast-instruct-gguf", + "downloads": 933, "source": "Hugging Face", - "score": -0.09752476631552795, - "first_commit": "2023-12-25 17:14:45", - "latest_commit": "2023-12-27 01:41:31", + "score": -0.08290058372585883, + "first_commit": "2023-12-27 09:46:04", + "latest_commit": "2023-12-27 11:39:18", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LlamaForCausalLM" + "model_size": 13.1, + "model_architectures": null }, { "description": "Japanese-StableLM-Instruct-Alpha-7B-v2 \"A parrot able to speak Japanese, ukiyoe, edo period\" — Stable Diffusion XL Model Description japanese-stablelm-instruct-alpha-7b-v2 is a 7B parameter decoder-only language models pre-trained built on top of the Japanese-StableLM-Base-Alpha-7B model and further fine-tuned on various instruction-following datasets.", "url": "https://huggingface.co/stabilityai/japanese-stablelm-instruct-alpha-7b-v2", "project_name": "japanese-stablelm-instruct-alpha-7b-v2", - "downloads": 1074, + "downloads": 903, "source": "Hugging Face", - "score": -0.0975719003856106, + "score": -0.08321873224194884, "first_commit": "2023-10-06 08:40:24", "latest_commit": "2023-10-06 08:40:24", "languages": [], @@ -4655,346 +4741,320 @@ "model_architectures": "JapaneseStableLMAlphaForCausalLM" }, { - "description": "🎈 FlexDreamHK FlexDreamHKはリークされたNovelAIモデルの入っていない、あるいはそのリスクを可能な限り低くしたモデルを目指して作成しました。 ", - "url": "https://huggingface.co/den2nova/FlexDreamHK", - "project_name": "FlexDreamHK", - "downloads": 1067, - "source": "Hugging Face", - "score": -0.09768187988247012, - "first_commit": "2023-07-06 10:11:45", - "latest_commit": "2023-07-29 04:21:29", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": null - }, - { - "description": "gpt-neox-japanese-2.7b", - "url": "https://huggingface.co/abeja/gpt-neox-japanese-2.7b", - "project_name": "gpt-neox-japanese-2.7b", - "downloads": 1066, + "description": "Orion-14B 🌐English | 🇨", + "url": "https://huggingface.co/OrionStarAI/Orion-14B-Base", + "project_name": "Orion-14B-Base", + "downloads": 898, "source": "Hugging Face", - "score": -0.09769759123916434, - "first_commit": "2022-08-29 02:15:44", - "latest_commit": "2023-04-10 05:12:30", + "score": -0.08327175699463052, + "first_commit": "2024-01-16 06:07:42", + "latest_commit": "2024-03-26 09:21:52", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "GPTNeoXJapaneseForCausalLM" + "model_architectures": "OrionForCausalLM" }, { - "description": "Ninja-v1-NSFW-gguf Local-Novel-LLM-projectさんが公開しているNinja-v1-NSFWのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Ninja-v1-NSFW-gguf", - "project_name": "Ninja-v1-NSFW-gguf", - "downloads": 1062, - "source": "Hugging Face", - "score": -0.0977604366659412, - "first_commit": "2024-05-03 14:03:23", - "latest_commit": "2024-05-04 13:26:52", - "languages": [], - "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": null + "description": "GUIで動作する文書校正ツール GUI tool for textlinting.", + "url": "https://github.com/gecko655/proofreading-tool", + "project_name": "proofreading-tool", + "stargazers_count": 86, + "source": "GitHub", + "score": -0.08327512784583407, + "first_commit": "2021-04-08 12:10:36", + "latest_commit": "2024-06-22 20:18:09", + "languages": [ + "JavaScript" + ], + "model_or_dataset": null }, { - "description": "japanese-large-lm-1.7b This repository provides a 1.7B parameters Japanese language model, trained by LINE Corporation.", - "url": "https://huggingface.co/line-corporation/japanese-large-lm-1.7b", - "project_name": "japanese-large-lm-1.7b", - "downloads": 1059, + "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", + "url": "https://huggingface.co/tokyotech-llm/Swallow-70b-hf", + "project_name": "Swallow-70b-hf", + "downloads": 895, "source": "Hugging Face", - "score": -0.09780757073602385, - "first_commit": "2023-07-21 00:46:33", - "latest_commit": "2023-08-17 01:06:37", + "score": -0.08330357184623952, + "first_commit": "2023-11-25 02:13:04", + "latest_commit": "2024-06-29 08:56:23", "languages": [], "model_or_dataset": "model", - "model_size": 1.75, - "model_architectures": "GPT2LMHeadModel" + "model_size": null, + "model_architectures": "LlamaForCausalLM" }, { - "description": "BERT Base Japanese for Irony", - "url": "https://huggingface.co/kit-nlp/bert-base-japanese-sentiment-irony", - "project_name": "bert-base-japanese-sentiment-irony", - "downloads": 1038, + "description": "HODACHI-Borea-Phi-3.5-mini-Instruct-Common-gguf HODACHIさんが公開しているBorea-Phi-3.5-mini-Instruct-Commonのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/HODACHI-Borea-Phi-3.5-mini-Instruct-Common-gguf", + "project_name": "HODACHI-Borea-Phi-3.5-mini-Instruct-Common-gguf", + "downloads": 892, "source": "Hugging Face", - "score": -0.09813750922660242, - "first_commit": "2022-11-07 06:29:21", - "latest_commit": "2022-11-08 04:23:27", + "score": -0.08333538669784851, + "first_commit": "2024-08-21 10:33:58", + "latest_commit": "2024-08-21 11:42:56", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForSequenceClassification" + "model_size": 3.82, + "model_architectures": null }, { - "description": "japanese-gpt-neox-3.6b-instruction-sft Overview This repository provides a Japanese GPT-NeoX model of 3.6 billion parameters.", - "url": "https://huggingface.co/rinna/japanese-gpt-neox-3.6b-instruction-sft", - "project_name": "japanese-gpt-neox-3.6b-instruction-sft", - "downloads": 1029, + "description": "🎈 FlexDreamHK FlexDreamHKはリークされたNovelAIモデルの入っていない、あるいはそのリスクを可能な限り低くしたモデルを目指して作成しました。 ", + "url": "https://huggingface.co/den2nova/FlexDreamHK", + "project_name": "FlexDreamHK", + "downloads": 889, "source": "Hugging Face", - "score": -0.09827891143685037, - "first_commit": "2023-05-17 02:16:28", - "latest_commit": "2024-07-20 07:56:34", + "score": -0.08336720154945752, + "first_commit": "2023-07-06 10:11:45", + "latest_commit": "2023-07-29 04:21:29", "languages": [], "model_or_dataset": "model", - "model_size": 3.76, - "model_architectures": "GPTNeoXForCausalLM" + "model_size": null, + "model_architectures": null }, { - "description": "OpenCALM-Medium Model Description OpenCALM is a suite of decoder-only language models pre-trained on Japanese datasets, developed by", - "url": "https://huggingface.co/cyberagent/open-calm-medium", - "project_name": "open-calm-medium", - "downloads": 1011, + "description": "Ruri: Japanese General Text Embeddings Usage Direct Usage (Sentence Transformers)", + "url": "https://huggingface.co/cl-nagoya/ruri-large", + "project_name": "ruri-large", + "downloads": 888, "source": "Hugging Face", - "score": -0.09856171585734627, - "first_commit": "2023-05-15 06:44:47", - "latest_commit": "2023-05-18 01:10:54", + "score": -0.08337780649999385, + "first_commit": "2024-08-28 17:11:42", + "latest_commit": "2024-09-04 08:49:10", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "GPTNeoXForCausalLM" + "model_size": 0.337, + "model_architectures": "BertModel" }, { - "description": "Model card for model ID", - "url": "https://huggingface.co/retrieva-jp/t5-small-short", - "project_name": "t5-small-short", - "downloads": 990, + "description": "Llama-3-ELYZA-JP-8B-AWQ Model Description Llama-3-ELYZA-JP-8B is a large language model trained by ELYZA, Inc.", + "url": "https://huggingface.co/elyza/Llama-3-ELYZA-JP-8B-AWQ", + "project_name": "Llama-3-ELYZA-JP-8B-AWQ", + "downloads": 858, "source": "Hugging Face", - "score": -0.09889165434792484, - "first_commit": "2023-04-25 04:37:20", - "latest_commit": "2023-05-10 09:55:39", + "score": -0.08369595501608387, + "first_commit": "2024-06-25 04:31:31", + "latest_commit": "2024-06-26 02:56:39", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "T5ForConditionalGeneration" + "model_size": 1.98, + "model_architectures": "LlamaForCausalLM" }, { - "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", - "url": "https://huggingface.co/tokyotech-llm/Swallow-70b-hf", - "project_name": "Swallow-70b-hf", - "downloads": 978, + "description": "Japanese StableLM-3B-4E1T Instruct Model Description", + "url": "https://huggingface.co/stabilityai/japanese-stablelm-3b-4e1t-instruct", + "project_name": "japanese-stablelm-3b-4e1t-instruct", + "downloads": 844, "source": "Hugging Face", - "score": -0.09908019062825545, - "first_commit": "2023-11-25 02:13:04", - "latest_commit": "2024-06-29 08:56:23", + "score": -0.08384442432359254, + "first_commit": "2023-10-16 07:50:31", + "latest_commit": "2024-04-26 03:20:42", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LlamaForCausalLM" + "model_size": 2.8, + "model_architectures": "StableLMEpochForCausalLM" }, { - "description": "japanese-large-lm-3.6b-instruction-sft", - "url": "https://huggingface.co/line-corporation/japanese-large-lm-3.6b-instruction-sft", - "project_name": "japanese-large-lm-3.6b-instruction-sft", - "downloads": 971, + "description": "llm-jp-13b-instruct-full-dolly_en-dolly_ja-ichikara_003_001-oasst_en-oasst_ja-v1.1", + "url": "https://huggingface.co/llm-jp/llm-jp-13b-instruct-full-dolly_en-dolly_ja-ichikara_003_001-oasst_en-oasst_ja-v1.1", + "project_name": "llm-jp-13b-instruct-full-dolly_en-dolly_ja-ichikara_003_001-oasst_en-oasst_ja-v1.1", + "downloads": 835, "source": "Hugging Face", - "score": -0.09919017012511495, - "first_commit": "2023-08-14 17:18:09", - "latest_commit": "2023-08-24 10:08:28", + "score": -0.08393986887841955, + "first_commit": "2024-01-29 12:52:31", + "latest_commit": "2024-02-07 19:49:25", "languages": [], "model_or_dataset": "model", - "model_size": 3.68, - "model_architectures": "GPTNeoXForCausalLM" + "model_size": 12.9, + "model_architectures": "GPT2LMHeadModel" }, { - "description": "Llama-3.1-70B-Instruct-gguf meta-llamaさんが公開しているMeta-Llama-3.1-70B-Instructのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Llama-3.1-70B-Instruct-gguf", - "project_name": "Llama-3.1-70B-Instruct-gguf", - "downloads": 967, + "description": "llm-jp-13b-instruct-lora-jaster-dolly-oasst-v1.0", + "url": "https://huggingface.co/llm-jp/llm-jp-13b-instruct-lora-jaster-dolly-oasst-v1.0", + "project_name": "llm-jp-13b-instruct-lora-jaster-dolly-oasst-v1.0", + "downloads": 820, "source": "Hugging Face", - "score": -0.09925301555189182, - "first_commit": "2024-07-23 17:25:23", - "latest_commit": "2024-07-24 21:04:27", + "score": -0.08409894313646456, + "first_commit": "2023-10-18 19:01:48", + "latest_commit": "2023-10-20 08:41:17", "languages": [], "model_or_dataset": "model", - "model_size": 70.6, + "model_size": null, "model_architectures": null }, { - "description": "PLaMo-13B-Instruct Model Description PLaMo-13B-Instruct is an instruct fine-tuned model built upon the 8192 context length version of PLaMo-13B text generation model.", - "url": "https://huggingface.co/pfnet/plamo-13b-instruct", - "project_name": "plamo-13b-instruct", - "downloads": 961, + "description": "t5-base-japanese-web (with Byte-fallback, 32K) Description megagonlabs/t5-base-japanese-web is a T5 (Text-to-Text Transfer Transformer) model pre-trained on Japanese web texts.", + "url": "https://huggingface.co/megagonlabs/t5-base-japanese-web", + "project_name": "t5-base-japanese-web", + "downloads": 814, "source": "Hugging Face", - "score": -0.09934728369205713, - "first_commit": "2023-10-26 02:11:24", - "latest_commit": "2024-01-25 07:46:09", + "score": -0.08416257283968255, + "first_commit": "2021-08-24 04:41:45", + "latest_commit": "2021-09-06 19:32:21", "languages": [], "model_or_dataset": "model", - "model_size": 13.1, - "model_architectures": "PlamoForCausalLM" + "model_size": null, + "model_architectures": "T5ForConditionalGeneration" }, { - "description": "Please feel free to open an issue or pull request. ", - "url": "https://huggingface.co/datasets/kumapo/JAQKET", - "project_name": "JAQKET", - "downloads": 956, + "description": "This is the filtered Japanese subset of XL-Sum followed by PaLM 2 filters 15-gram overlap * code: https://gist.github.com/mkshing/d6371cbfdd50d4f352cee247fd4dd86a number of examples train: 4215 (before: 7113) validation: 758 (before: 889) test: 766 (before: 889)", + "url": "https://huggingface.co/datasets/mkshing/xlsum_ja", + "project_name": "xlsum_ja", + "downloads": 798, "source": "Hugging Face", - "score": -0.09942584047552822, - "first_commit": "2023-06-21 13:04:38", - "latest_commit": "2023-10-09 06:44:28", + "score": -0.0843322520482639, + "first_commit": "2023-06-16 04:15:41", + "latest_commit": "2023-06-20 23:28:48", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "LLaVA-JP Model Card Model detail Model type: LLaVA-JP is a vision-language model that can converse about input images.", - "url": "https://huggingface.co/toshi456/llava-jp-1.3b-v1.0", - "project_name": "llava-jp-1.3b-v1.0", - "downloads": 951, + "description": "shisa-base-7b-v1 shisa-base-7b-v1 takes Mistral 7B and adds an additional 8B tokens of primarily Japanese pre-training.", + "url": "https://huggingface.co/augmxnt/shisa-base-7b-v1", + "project_name": "shisa-base-7b-v1", + "downloads": 755, "source": "Hugging Face", - "score": -0.0995043972589993, - "first_commit": "2023-12-04 13:13:03", - "latest_commit": "2023-12-18 10:21:11", + "score": -0.08478826492132625, + "first_commit": "2023-11-19 09:44:36", + "latest_commit": "2023-12-09 10:34:29", "languages": [], "model_or_dataset": "model", - "model_size": 1.73, - "model_architectures": "LlavaGpt2ForCausalLM" + "model_size": 7.96, + "model_architectures": "MistralForCausalLM" }, { - "description": "Model Card for Japanese BART base Model description This is a Japanese BART base model pre-trained on Japanese Wikipedia.", - "url": "https://huggingface.co/ku-nlp/bart-base-japanese", - "project_name": "bart-base-japanese", - "downloads": 942, + "description": "Shisa 7B Shisa 7B (shisa-7b-v1)", + "url": "https://huggingface.co/augmxnt/shisa-7b-v1", + "project_name": "shisa-7b-v1", + "downloads": 754, "source": "Hugging Face", - "score": -0.09964579946924726, - "first_commit": "2023-05-09 07:00:51", - "latest_commit": "2023-05-12 11:03:20", + "score": -0.0847988698718626, + "first_commit": "2023-11-27 17:55:31", + "latest_commit": "2023-12-20 18:11:13", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "MBartForConditionalGeneration" + "model_size": 7.96, + "model_architectures": "MistralForCausalLM" }, { - "description": "HODACHI-Borea-Phi-3.5-mini-Instruct-Jp-gguf HODACHIさんが公開しているBorea-Phi-3.5-mini-Instruct-Jpのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/HODACHI-Borea-Phi-3.5-mini-Instruct-Jp-gguf", - "project_name": "HODACHI-Borea-Phi-3.5-mini-Instruct-Jp-gguf", - "downloads": 942, + "description": "haqishen-Llama-3-8B-Japanese-Instruct-gguf haqishenさんが公開しているLlama-3-8B-Japanese-Instructのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/haqishen-Llama-3-8B-Japanese-Instruct-gguf", + "project_name": "haqishen-Llama-3-8B-Japanese-Instruct-gguf", + "downloads": 753, "source": "Hugging Face", - "score": -0.09964579946924726, - "first_commit": "2024-08-21 09:58:41", - "latest_commit": "2024-08-21 11:08:38", + "score": -0.08480947482239892, + "first_commit": "2024-04-23 13:55:17", + "latest_commit": "2024-04-23 14:54:23", "languages": [], "model_or_dataset": "model", - "model_size": 3.82, + "model_size": 8.03, "model_architectures": null }, { - "description": "HODACHI-EZO-Common-T2-2B-gemma-2-it-gguf HODACHIさんが公開しているEZO-Common-T2-2B-gemma-2-itのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/HODACHI-EZO-Common-T2-2B-gemma-2-it-gguf", - "project_name": "HODACHI-EZO-Common-T2-2B-gemma-2-it-gguf", - "downloads": 928, + "description": "Model Card for Model ID Original model elyza/ELYZA-japanese-Llama-2-7b-fast-instruct which is based on Meta's \"Llama 2\" and has undergone additional pre-training in Japanese, and thier original post-training and speed up tuning.", + "url": "https://huggingface.co/dahara1/ELYZA-japanese-Llama-2-7b-fast-instruct-GPTQ", + "project_name": "ELYZA-japanese-Llama-2-7b-fast-instruct-GPTQ", + "downloads": 734, "source": "Hugging Face", - "score": -0.09986575846296629, - "first_commit": "2024-08-01 17:32:31", - "latest_commit": "2024-08-01 18:38:31", + "score": -0.08501096888258927, + "first_commit": "2023-08-30 09:18:50", + "latest_commit": "2023-11-14 00:10:58", "languages": [], "model_or_dataset": "model", - "model_size": 2.61, - "model_architectures": null + "model_size": 1.24, + "model_architectures": "LlamaForCausalLM" }, { - "description": "databricks/dolly-v2-12b の学習データに使用されたdatabricks-dolly-15k.jsonl を日本語に翻訳したデータセットになります。", - "url": "https://github.com/kunishou/databricks-dolly-15k-ja", - "project_name": "databricks-dolly-15k-ja", - "stargazers_count": 81, - "source": "GitHub", - "score": -0.09988319288674681, - "first_commit": "2023-04-14 23:43:27", - "latest_commit": "2023-07-26 00:08:32", + "description": "Tanuki-8x8B-dpo-v1.0-AWQ 概要 GENIAC 松尾研 LLM開発プロジェクトで開発されたLLMであるweblab-GENIAC/Tanuki-8x8B-dpo-v1.0のAWQ 4bit量子化モデルです。", + "url": "https://huggingface.co/team-hatakeyama-phase2/Tanuki-8x8B-dpo-v1.0-AWQ", + "project_name": "Tanuki-8x8B-dpo-v1.0-AWQ", + "downloads": 732, + "source": "Hugging Face", + "score": -0.08503217878366193, + "first_commit": "2024-08-27 09:31:22", + "latest_commit": "2024-09-03 09:26:20", "languages": [], - "model_or_dataset": "dataset" + "model_or_dataset": "model", + "model_size": 6.75, + "model_architectures": "TanukiForCausalLM" }, { - "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", - "url": "https://huggingface.co/tokyotech-llm/Swallow-70b-instruct-v0.1", - "project_name": "Swallow-70b-instruct-v0.1", - "downloads": 925, + "description": "weblab-10b-instruction-sft-GPTQ Original model weblab-10b-instruction-sft which is a Japanese-centric multilingual GPT-NeoX model of 10 billion parameters created by matsuo-lab Takeshi Kojima.", + "url": "https://huggingface.co/dahara1/weblab-10b-instruction-sft-GPTQ", + "project_name": "weblab-10b-instruction-sft-GPTQ", + "downloads": 723, "source": "Hugging Face", - "score": -0.09991289253304894, - "first_commit": "2024-03-06 14:39:34", - "latest_commit": "2024-06-29 09:00:17", + "score": -0.08512762333848894, + "first_commit": "2023-08-21 05:45:35", + "latest_commit": "2023-11-14 00:24:22", "languages": [], "model_or_dataset": "model", - "model_size": 69.2, - "model_architectures": "LlamaForCausalLM" + "model_size": 1.86, + "model_architectures": "GPTNeoXForCausalLM" }, { - "description": "Llama-3.1-70B-EZO-1.1-it-gguf HODACHIさんが公開しているLlama-3.1-70B-EZO-1.1-itのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Llama-3.1-70B-EZO-1.1-it-gguf", - "project_name": "Llama-3.1-70B-EZO-1.1-it-gguf", - "downloads": 881, + "description": "Tanuki-8B-dpo-v1.0-GGUF 概要 GENIAC 松尾研 LLM開発プロジェクトで開発されたLLMであるweblab-GENIAC/Tanuki-8B-dpo-v1.0のGGUF量子化モデルです。", + "url": "https://huggingface.co/team-hatakeyama-phase2/Tanuki-8B-dpo-v1.0-GGUF", + "project_name": "Tanuki-8B-dpo-v1.0-GGUF", + "downloads": 720, "source": "Hugging Face", - "score": -0.1006041922275945, - "first_commit": "2024-07-31 12:12:13", - "latest_commit": "2024-07-31 21:47:25", + "score": -0.08515943819009794, + "first_commit": "2024-08-14 15:05:50", + "latest_commit": "2024-08-27 18:00:44", "languages": [], "model_or_dataset": "model", - "model_size": 70.6, + "model_size": 7.51, "model_architectures": null }, { - "description": "hotchpotch/japanese-reranker-cross-encoder-base-v1 日本語で学習させた Reranker (CrossEncoder) シリーズです。 ", - "url": "https://huggingface.co/hotchpotch/japanese-reranker-cross-encoder-base-v1", - "project_name": "japanese-reranker-cross-encoder-base-v1", - "downloads": 865, - "source": "Hugging Face", - "score": -0.10085557393470197, - "first_commit": "2024-03-29 07:07:38", - "latest_commit": "2024-04-01 02:39:31", - "languages": [], - "model_or_dataset": "model", - "model_size": 0.111, - "model_architectures": "BertForSequenceClassification" - }, - { - "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", - "url": "https://huggingface.co/tokyotech-llm/Swallow-7b-plus-hf", - "project_name": "Swallow-7b-plus-hf", - "downloads": 864, + "description": "japanese-stablelm-2-instruct-1_6b-gguf stabilityaiさんが公開しているjapanese-stablelm-2-instruct-1_6bのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/japanese-stablelm-2-instruct-1_6b-gguf", + "project_name": "japanese-stablelm-2-instruct-1_6b-gguf", + "downloads": 708, "source": "Hugging Face", - "score": -0.10087128529139619, - "first_commit": "2024-02-29 11:28:52", - "latest_commit": "2024-06-29 08:56:19", + "score": -0.08528669759653394, + "first_commit": "2024-05-11 07:26:43", + "latest_commit": "2024-05-11 09:56:19", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LlamaForCausalLM" + "model_size": 1.64, + "model_architectures": null }, { - "description": "nlp-waseda/roberta-large-japanese-seq512 Model description This is a Japanese RoBERTa large model pretrained on Japanese Wikipedia and the Japanese portion of CC-100 with the maximum sequence length of 512.", - "url": "https://huggingface.co/nlp-waseda/roberta-large-japanese-seq512", - "project_name": "roberta-large-japanese-seq512", - "downloads": 840, + "description": "Llama-3-Swallow-8B-Instruct-v0.1-gguf tokyotech-llmさんが公開しているLlama-3-Swallow-8B-Instruct-v0.1のggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Llama-3-Swallow-8B-Instruct-v0.1-gguf", + "project_name": "Llama-3-Swallow-8B-Instruct-v0.1-gguf", + "downloads": 705, "source": "Hugging Face", - "score": -0.1012483578520574, - "first_commit": "2022-06-13 09:46:45", - "latest_commit": "2022-10-21 14:49:40", + "score": -0.08531851244814295, + "first_commit": "2024-07-01 16:42:54", + "latest_commit": "2024-07-02 10:43:55", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "RobertaForMaskedLM" + "model_size": 8.03, + "model_architectures": null }, { - "description": "HODACHI-Borea-Phi-3.5-mini-Instruct-Common-gguf HODACHIさんが公開しているBorea-Phi-3.5-mini-Instruct-Commonのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/HODACHI-Borea-Phi-3.5-mini-Instruct-Common-gguf", - "project_name": "HODACHI-Borea-Phi-3.5-mini-Instruct-Common-gguf", - "downloads": 832, + "description": "Japanese-LLaMA-3-8B-Instruct-v2 Japanese-LLaMA-3-8B-Instruct-v2は指示実行モデル、フルモデルです。 ", + "url": "https://huggingface.co/owner203/japanese-llama-3-8b-instruct-v2", + "project_name": "japanese-llama-3-8b-instruct-v2", + "downloads": 705, "source": "Hugging Face", - "score": -0.10137404870561113, - "first_commit": "2024-08-21 10:33:58", - "latest_commit": "2024-08-21 11:42:56", + "score": -0.08531851244814295, + "first_commit": "2024-06-10 10:10:19", + "latest_commit": "2024-06-21 06:35:31", "languages": [], "model_or_dataset": "model", - "model_size": 3.82, - "model_architectures": null + "model_size": 8.03, + "model_architectures": "LlamaForCausalLM" }, { "description": "ODEX is an Open-Domain EXecution-based NL-to-Code generation data benchmark.", "url": "https://huggingface.co/datasets/neulab/odex", "project_name": "odex", - "downloads": 809, + "downloads": 694, "source": "Hugging Face", - "score": -0.10173540990957813, + "score": -0.08543516690404263, "first_commit": "2023-01-06 14:30:00", "latest_commit": "2023-02-10 18:01:34", "languages": [], @@ -5003,654 +5063,642 @@ "model_architectures": null }, { - "description": "stockmark/stockmark-100b Stockmark-100b is a 100 billion parameter LLM pretrained from scratch based on Japanese and English corpus of about 910 billion tokens.", - "url": "https://huggingface.co/stockmark/stockmark-100b", - "project_name": "stockmark-100b", - "downloads": 803, + "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", + "url": "https://huggingface.co/tokyotech-llm/Swallow-70b-instruct-v0.1", + "project_name": "Swallow-70b-instruct-v0.1", + "downloads": 693, "source": "Hugging Face", - "score": -0.10182967804974342, - "first_commit": "2024-05-13 09:31:40", - "latest_commit": "2024-05-15 06:18:10", + "score": -0.08544577185457895, + "first_commit": "2024-03-06 14:39:34", + "latest_commit": "2024-06-29 09:00:17", "languages": [], "model_or_dataset": "model", - "model_size": 96.2, + "model_size": 69.2, "model_architectures": "LlamaForCausalLM" }, { - "description": "This is the filtered Japanese subset of XL-Sum followed by PaLM 2 filters 15-gram overlap * code: https://gist.github.com/mkshing/d6371cbfdd50d4f352cee247fd4dd86a number of examples train: 4215 (before: 7113) validation: 758 (before: 889) test: 766 (before: 889)", - "url": "https://huggingface.co/datasets/mkshing/xlsum_ja", - "project_name": "xlsum_ja", - "downloads": 802, + "description": "Japanese-StableLM-Instruct-Beta-7B A cute robot wearing a kimono writes calligraphy with one single brush — Stable Diffusion XL Model Description japanese-stablelm-instruct-beta-7b is a 7B-parameter decoder-only language model based on", + "url": "https://huggingface.co/stabilityai/japanese-stablelm-instruct-beta-7b", + "project_name": "japanese-stablelm-instruct-beta-7b", + "downloads": 667, "source": "Hugging Face", - "score": -0.10184538940643764, - "first_commit": "2023-06-16 04:15:41", - "latest_commit": "2023-06-20 23:28:48", + "score": -0.08572150056852364, + "first_commit": "2023-10-30 07:47:09", + "latest_commit": "2023-12-19 06:43:49", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null + "model_or_dataset": "model", + "model_size": 6.74, + "model_architectures": "LlamaForCausalLM" }, { - "description": "Japanese StableLM-3B-4E1T Instruct Model Description", - "url": "https://huggingface.co/stabilityai/japanese-stablelm-3b-4e1t-instruct", - "project_name": "japanese-stablelm-3b-4e1t-instruct", - "downloads": 791, + "description": "gpt2-large-japanese This repository provides a large sized Japanese GPT-2 model.", + "url": "https://huggingface.co/abeja/gpt2-large-japanese", + "project_name": "gpt2-large-japanese", + "downloads": 667, "source": "Hugging Face", - "score": -0.10201821433007403, - "first_commit": "2023-10-16 07:50:31", - "latest_commit": "2024-04-26 03:20:42", + "score": -0.08572150056852364, + "first_commit": "2022-08-29 05:17:36", + "latest_commit": "2022-08-29 16:10:11", "languages": [], "model_or_dataset": "model", - "model_size": 2.8, - "model_architectures": "StableLMEpochForCausalLM" + "model_size": null, + "model_architectures": "GPT2LMHeadModel" }, { - "description": "Llama-3-ELYZA-JP-8B-AWQ Model Description Llama-3-ELYZA-JP-8B is a large language model trained by ELYZA, Inc.", - "url": "https://huggingface.co/elyza/Llama-3-ELYZA-JP-8B-AWQ", - "project_name": "Llama-3-ELYZA-JP-8B-AWQ", - "downloads": 782, + "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", + "url": "https://huggingface.co/tokyotech-llm/Swallow-70b-NVE-instruct-hf", + "project_name": "Swallow-70b-NVE-instruct-hf", + "downloads": 667, "source": "Hugging Face", - "score": -0.10215961654032199, - "first_commit": "2024-06-25 04:31:31", - "latest_commit": "2024-06-26 02:56:39", + "score": -0.08572150056852364, + "first_commit": "2023-12-13 03:56:30", + "latest_commit": "2024-07-06 15:18:24", "languages": [], "model_or_dataset": "model", - "model_size": 1.98, + "model_size": 69.0, "model_architectures": "LlamaForCausalLM" }, { - "description": "ELYZA-japanese-Llama-2-7b-fast-gguf ELYZAさんが公開しているELYZA-japanese-Llama-2-7b-fastのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-7b-fast-gguf", - "project_name": "ELYZA-japanese-Llama-2-7b-fast-gguf", - "downloads": 760, + "description": "Polyglot-math-4x7b-24b Polyglot-4x7b is a Mixture of Experts approach to a multilingual model.", + "url": "https://huggingface.co/macadeliccc/polyglot-math-4x7b", + "project_name": "polyglot-math-4x7b", + "downloads": 657, "source": "Hugging Face", - "score": -0.10250526638759476, - "first_commit": "2023-08-29 07:23:20", - "latest_commit": "2023-11-16 14:27:36", + "score": -0.08582755007388697, + "first_commit": "2024-01-13 03:05:44", + "latest_commit": "2024-03-04 19:25:12", "languages": [], "model_or_dataset": "model", - "model_size": 6.85, + "model_size": 24.2, + "model_architectures": "MixtralForCausalLM" + }, + { + "description": "Ninja-v1-gguf Local-Novel-LLM-projectさんが公開しているNinja-v1のggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Ninja-v1-gguf", + "project_name": "Ninja-v1-gguf", + "downloads": 648, + "source": "Hugging Face", + "score": -0.08592299462871397, + "first_commit": "2024-05-03 14:03:22", + "latest_commit": "2024-05-04 13:26:22", + "languages": [], + "model_or_dataset": "model", + "model_size": 7.24, "model_architectures": null }, { - "description": "Shisa 7B Shisa 7B (shisa-7b-v1)", - "url": "https://huggingface.co/augmxnt/shisa-7b-v1", - "project_name": "shisa-7b-v1", - "downloads": 754, + "description": "rinna/nekomata-14b Overview We conduct continual pre-training of qwen-14b on 66B tokens from a mixture of Japanese and English datasets.", + "url": "https://huggingface.co/rinna/nekomata-14b", + "project_name": "nekomata-14b", + "downloads": 646, "source": "Hugging Face", - "score": -0.10259953452776006, - "first_commit": "2023-11-27 17:55:31", - "latest_commit": "2023-12-20 18:11:13", + "score": -0.08594420452978664, + "first_commit": "2023-12-19 08:09:53", + "latest_commit": "2024-07-22 07:58:40", "languages": [], "model_or_dataset": "model", - "model_size": 7.96, - "model_architectures": "MistralForCausalLM" + "model_size": 14.2, + "model_architectures": "QWenLMHeadModel" }, { - "description": "shisa-base-7b-v1 shisa-base-7b-v1 takes Mistral 7B and adds an additional 8B tokens of primarily Japanese pre-training.", - "url": "https://huggingface.co/augmxnt/shisa-base-7b-v1", - "project_name": "shisa-base-7b-v1", - "downloads": 749, + "description": "stockmark/stockmark-100b Stockmark-100b is a 100 billion parameter LLM pretrained from scratch based on Japanese and English corpus of about 910 billion tokens.", + "url": "https://huggingface.co/stockmark/stockmark-100b", + "project_name": "stockmark-100b", + "downloads": 645, "source": "Hugging Face", - "score": -0.10267809131123115, - "first_commit": "2023-11-19 09:44:36", - "latest_commit": "2023-12-09 10:34:29", + "score": -0.08595480948032298, + "first_commit": "2024-05-13 09:31:40", + "latest_commit": "2024-05-15 06:18:10", "languages": [], "model_or_dataset": "model", - "model_size": 7.96, - "model_architectures": "MistralForCausalLM" + "model_size": 96.2, + "model_architectures": "LlamaForCausalLM" }, { - "description": "Python library for CJK (Chinese, Japanese, and Korean) language dictionary", - "url": "https://github.com/cihai/cihai", - "project_name": "cihai", - "stargazers_count": 80, + "description": "Tanuki-8x8B-dpo-v1.0-GGUF 概要 GENIAC 松尾研 LLM開発プロジェクトで開発されたLLMであるweblab-GENIAC/Tanuki-8x8B-dpo-v1.0のGGUF量子化モデルです。", + "url": "https://huggingface.co/team-hatakeyama-phase2/Tanuki-8x8B-dpo-v1.0-GGUF", + "project_name": "Tanuki-8x8B-dpo-v1.0-GGUF", + "downloads": 627, + "source": "Hugging Face", + "score": -0.08614569858997699, + "first_commit": "2024-08-14 18:48:45", + "latest_commit": "2024-08-29 17:42:37", + "languages": [], + "model_or_dataset": "model", + "model_size": 47.0, + "model_architectures": null + }, + { + "description": "Corpus of Annual Reports in Japan", + "url": "https://github.com/chakki-works/CoARiJ", + "project_name": "CoARiJ", + "stargazers_count": 85, "source": "GitHub", - "score": -0.1028147348993446, - "first_commit": "2013-12-03 09:42:52", - "latest_commit": "2024-08-10 13:13:53", + "score": -0.08621514840710377, + "first_commit": "2019-09-02 14:12:48", + "latest_commit": "2020-12-19 14:00:34", "languages": [ "Python" ], - "model_or_dataset": null - }, - { - "description": "Neologism dictionary based on the language resources on the Web for mecab-unidic", - "url": "https://github.com/neologd/mecab-unidic-neologd", - "project_name": "mecab-unidic-neologd", - "stargazers_count": 80, - "source": "GitHub", - "score": -0.1028147348993446, - "first_commit": "2015-03-19 10:52:02", - "latest_commit": "2020-09-14 19:58:39", - "languages": [], "model_or_dataset": "dataset" }, { - "description": "Orion-14B 🌐English | 🇨", - "url": "https://huggingface.co/OrionStarAI/Orion-14B-Base", - "project_name": "Orion-14B-Base", - "downloads": 735, + "description": "このモデルは何？ ", + "url": "https://huggingface.co/Lasorco/lametta", + "project_name": "lametta", + "downloads": 619, "source": "Hugging Face", - "score": -0.1028980503049502, - "first_commit": "2024-01-16 06:07:42", - "latest_commit": "2024-03-26 09:21:52", + "score": -0.08623053819426765, + "first_commit": "2023-03-28 14:29:55", + "latest_commit": "2023-11-08 07:37:12", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "OrionForCausalLM" + "model_architectures": null }, { - "description": "weblab-10b-instruction-sft-GPTQ Original model weblab-10b-instruction-sft which is a Japanese-centric multilingual GPT-NeoX model of 10 billion parameters created by matsuo-lab Takeshi Kojima.", - "url": "https://huggingface.co/dahara1/weblab-10b-instruction-sft-GPTQ", - "project_name": "weblab-10b-instruction-sft-GPTQ", - "downloads": 716, + "description": "japanese-gpt-neox-3.6b-instruction-sft-v2 Overview", + "url": "https://huggingface.co/rinna/japanese-gpt-neox-3.6b-instruction-sft-v2", + "project_name": "japanese-gpt-neox-3.6b-instruction-sft-v2", + "downloads": 616, "source": "Hugging Face", - "score": -0.10319656608214031, - "first_commit": "2023-08-21 05:45:35", - "latest_commit": "2023-11-14 00:24:22", + "score": -0.08626235304587666, + "first_commit": "2023-05-30 01:50:25", + "latest_commit": "2024-07-20 07:57:35", "languages": [], "model_or_dataset": "model", - "model_size": 1.86, + "model_size": 3.76, "model_architectures": "GPTNeoXForCausalLM" }, { - "description": "Model Card for Model ID Original model elyza/ELYZA-japanese-Llama-2-7b-fast-instruct which is based on Meta's \"Llama 2\" and has undergone additional pre-training in Japanese, and thier original post-training and speed up tuning.", - "url": "https://huggingface.co/dahara1/ELYZA-japanese-Llama-2-7b-fast-instruct-GPTQ", - "project_name": "ELYZA-japanese-Llama-2-7b-fast-instruct-GPTQ", - "downloads": 714, + "description": "rinna-llama-3-youko-8b-gguf rinnaさんが公開しているllama-3-youko-8bのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/rinna-llama-3-youko-8b-gguf", + "project_name": "rinna-llama-3-youko-8b-gguf", + "downloads": 601, "source": "Hugging Face", - "score": -0.10322798879552875, - "first_commit": "2023-08-30 09:18:50", - "latest_commit": "2023-11-14 00:10:58", + "score": -0.08642142730392167, + "first_commit": "2024-05-01 14:17:53", + "latest_commit": "2024-05-01 15:11:21", "languages": [], "model_or_dataset": "model", - "model_size": 1.24, - "model_architectures": "LlamaForCausalLM" + "model_size": 8.03, + "model_architectures": null }, { - "description": "[Llama-3-EZO model card]", - "url": "https://huggingface.co/AXCXEPT/Llama-3-EZO-8b-Common-it", - "project_name": "Llama-3-EZO-8b-Common-it", - "downloads": 713, + "description": "albert-base-japanese-v1 日本語事前学習済みALBERTモデルです", + "url": "https://huggingface.co/ken11/albert-base-japanese-v1", + "project_name": "albert-base-japanese-v1", + "downloads": 601, "source": "Hugging Face", - "score": -0.10324370015222296, - "first_commit": "2024-07-13 06:42:31", - "latest_commit": "2024-08-23 10:52:05", + "score": -0.08642142730392167, + "first_commit": "2021-12-19 17:07:14", + "latest_commit": "2021-12-22 03:04:30", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": "LlamaForCausalLM" + "model_size": null, + "model_architectures": "AlbertForMaskedLM" }, { - "description": "Parakeet TDT-CTC 0.6B (ja) | | parakeet-tdt_ctc-0.6b-ja is an ASR model that transcribes Japanese speech with Punctuations.", - "url": "https://huggingface.co/nvidia/parakeet-tdt_ctc-0.6b-ja", - "project_name": "parakeet-tdt_ctc-0.6b-ja", - "downloads": 708, + "description": "PLaMo-13B-Instruct-NC Model Description PLaMo-13B-Instruct-NC is a noncommercial instruct fine-tuned model built upon the 8192 context length version of PLaMo-13B text generation model.", + "url": "https://huggingface.co/pfnet/plamo-13b-instruct-nc", + "project_name": "plamo-13b-instruct-nc", + "downloads": 596, "source": "Hugging Face", - "score": -0.10332225693569405, - "first_commit": "2024-05-13 15:39:30", - "latest_commit": "2024-05-17 17:20:17", + "score": -0.08647445205660334, + "first_commit": "2023-10-26 05:36:26", + "latest_commit": "2024-01-25 07:46:45", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": null + "model_size": 13.1, + "model_architectures": "PlamoForCausalLM" }, { - "description": "Orion-14B 🌐English | 🇨", - "url": "https://huggingface.co/OrionStarAI/Orion-14B-Chat", - "project_name": "Orion-14B-Chat", - "downloads": 706, + "description": "※llama.cpp Releases b3428(7/21)", + "url": "https://huggingface.co/MCZK/EZO-Common-9B-gemma-2-it-GGUF", + "project_name": "EZO-Common-9B-gemma-2-it-GGUF", + "downloads": 586, "source": "Hugging Face", - "score": -0.10335367964908249, - "first_commit": "2024-01-16 06:03:30", - "latest_commit": "2024-04-11 10:48:51", + "score": -0.08658050156196667, + "first_commit": "2024-07-10 11:12:59", + "latest_commit": "2024-07-21 11:26:08", "languages": [], "model_or_dataset": "model", - "model_size": 14.5, - "model_architectures": "OrionForCausalLM" + "model_size": 9.24, + "model_architectures": null }, { - "description": "bilingual-gpt-neox-4b-8k Overview Notice: This model requires transformers>=4.31.0 to work properly.", - "url": "https://huggingface.co/rinna/bilingual-gpt-neox-4b-8k", - "project_name": "bilingual-gpt-neox-4b-8k", - "downloads": 688, + "description": "Chat & support: TheBloke's Discord server Want to contribute?", + "url": "https://huggingface.co/TheBloke/japanese-stablelm-instruct-beta-70B-GGUF", + "project_name": "japanese-stablelm-instruct-beta-70B-GGUF", + "downloads": 586, "source": "Hugging Face", - "score": -0.1036364840695784, - "first_commit": "2023-07-31 02:34:21", - "latest_commit": "2024-07-20 08:03:16", + "score": -0.08658050156196667, + "first_commit": "2023-11-02 15:45:24", + "latest_commit": "2023-11-02 18:22:05", "languages": [], "model_or_dataset": "model", - "model_size": 3.95, - "model_architectures": "GPTNeoXForCausalLM" + "model_size": 69.0, + "model_architectures": null }, { - "description": "stockmark/gpt-neox-japanese-1.4b This repository provides a GPT-NeoX based model with 1.4B parameters pre-trained on Japanese corpus of about 20B tokens.", - "url": "https://huggingface.co/stockmark/gpt-neox-japanese-1.4b", - "project_name": "gpt-neox-japanese-1.4b", - "downloads": 677, + "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", + "url": "https://huggingface.co/tokyotech-llm/Swallow-70b-NVE-hf", + "project_name": "Swallow-70b-NVE-hf", + "downloads": 583, "source": "Hugging Face", - "score": -0.10380930899321479, - "first_commit": "2023-08-06 07:37:38", - "latest_commit": "2023-09-07 03:44:19", + "score": -0.08661231641357568, + "first_commit": "2023-12-07 07:34:35", + "latest_commit": "2024-06-29 08:56:25", "languages": [], "model_or_dataset": "model", - "model_size": 1.44, - "model_architectures": "GPTNeoXForCausalLM" + "model_size": null, + "model_architectures": "LlamaForCausalLM" }, { - "description": "hotchpotch/japanese-bge-reranker-v2-m3-v1 日本語で学習させた Reranker (CrossEncoder) シリーズです。 ", - "url": "https://huggingface.co/hotchpotch/japanese-bge-reranker-v2-m3-v1", - "project_name": "japanese-bge-reranker-v2-m3-v1", - "downloads": 673, + "description": "ichikara-instruction (Non Commercial) LLMのための日本語インストラクションデータ 公開ページ 公開ページより、 本データに関して、言語処理学会第３０回年次大会において発表を行います。", + "url": "https://huggingface.co/datasets/p1atdev/ichikara-instruction", + "project_name": "ichikara-instruction", + "downloads": 580, "source": "Hugging Face", - "score": -0.10387215441999165, - "first_commit": "2024-03-28 20:45:16", - "latest_commit": "2024-04-01 02:40:22", + "score": -0.08664413126518468, + "first_commit": "2024-03-12 07:09:56", + "latest_commit": "2024-03-12 08:36:40", "languages": [], - "model_or_dataset": "model", - "model_size": 0.5680000000000001, - "model_architectures": "XLMRobertaForSequenceClassification" + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null }, { - "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", - "url": "https://huggingface.co/tokyotech-llm/Swallow-70b-NVE-instruct-hf", - "project_name": "Swallow-70b-NVE-instruct-hf", - "downloads": 671, + "description": "KARAKURI LM KARAKURI LM is a pretrained language model that builds upon Llama 2.", + "url": "https://huggingface.co/karakuri-ai/karakuri-lm-70b-v0.1", + "project_name": "karakuri-lm-70b-v0.1", + "downloads": 576, "source": "Hugging Face", - "score": -0.10390357713338008, - "first_commit": "2023-12-13 03:56:30", - "latest_commit": "2024-07-06 15:18:24", + "score": -0.08668655106733002, + "first_commit": "2024-01-26 10:49:53", + "latest_commit": "2024-05-07 09:00:06", "languages": [], "model_or_dataset": "model", - "model_size": 69.0, + "model_size": 69.2, "model_architectures": "LlamaForCausalLM" }, { - "description": "japanese-stablelm-2-instruct-1_6b-gguf stabilityaiさんが公開しているjapanese-stablelm-2-instruct-1_6bのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/japanese-stablelm-2-instruct-1_6b-gguf", - "project_name": "japanese-stablelm-2-instruct-1_6b-gguf", - "downloads": 663, + "description": "stockmark/gpt-neox-japanese-1.4b This repository provides a GPT-NeoX based model with 1.4B parameters pre-trained on Japanese corpus of about 20B tokens.", + "url": "https://huggingface.co/stockmark/gpt-neox-japanese-1.4b", + "project_name": "gpt-neox-japanese-1.4b", + "downloads": 569, "source": "Hugging Face", - "score": -0.10402926798693382, - "first_commit": "2024-05-11 07:26:43", - "latest_commit": "2024-05-11 09:56:19", + "score": -0.08676078572108435, + "first_commit": "2023-08-06 07:37:38", + "latest_commit": "2023-09-07 03:44:19", "languages": [], "model_or_dataset": "model", - "model_size": 1.64, - "model_architectures": null + "model_size": 1.44, + "model_architectures": "GPTNeoXForCausalLM" }, { - "description": "gpt2-large-japanese This repository provides a large sized Japanese GPT-2 model.", - "url": "https://huggingface.co/abeja/gpt2-large-japanese", - "project_name": "gpt2-large-japanese", - "downloads": 659, + "description": "japanese-large-lm-1.7b-instruction-sft This repository provides a 1.7B parameters Japanese language model, fine-tuned and trained by LINE Corporation.", + "url": "https://huggingface.co/line-corporation/japanese-large-lm-1.7b-instruction-sft", + "project_name": "japanese-large-lm-1.7b-instruction-sft", + "downloads": 566, "source": "Hugging Face", - "score": -0.10409211341371069, - "first_commit": "2022-08-29 05:17:36", - "latest_commit": "2022-08-29 16:10:11", + "score": -0.08679260057269335, + "first_commit": "2023-08-14 17:19:11", + "latest_commit": "2023-08-14 17:19:11", "languages": [], "model_or_dataset": "model", "model_size": null, "model_architectures": "GPT2LMHeadModel" }, { - "description": "Polyglot-math-4x7b-24b Polyglot-4x7b is a Mixture of Experts approach to a multilingual model.", - "url": "https://huggingface.co/macadeliccc/polyglot-math-4x7b", - "project_name": "polyglot-math-4x7b", - "downloads": 658, + "description": "[Llama-3-EZO model card]", + "url": "https://huggingface.co/AXCXEPT/Llama-3-EZO-8b-Common-it", + "project_name": "Llama-3-EZO-8b-Common-it", + "downloads": 564, "source": "Hugging Face", - "score": -0.10410782477040491, - "first_commit": "2024-01-13 03:05:44", - "latest_commit": "2024-03-04 19:25:12", + "score": -0.08681381047376602, + "first_commit": "2024-07-13 06:42:31", + "latest_commit": "2024-08-23 10:52:05", "languages": [], "model_or_dataset": "model", - "model_size": 24.2, - "model_architectures": "MixtralForCausalLM" + "model_size": 8.03, + "model_architectures": "LlamaForCausalLM" }, { - "description": "Japanese-StableLM-Instruct-Beta-7B A cute robot wearing a kimono writes calligraphy with one single brush — Stable Diffusion XL Model Description japanese-stablelm-instruct-beta-7b is a 7B-parameter decoder-only language model based on", - "url": "https://huggingface.co/stabilityai/japanese-stablelm-instruct-beta-7b", - "project_name": "japanese-stablelm-instruct-beta-7b", - "downloads": 656, + "description": "オリジナルのサイトと同じものを使用しています。 ", + "url": "https://huggingface.co/datasets/llm-book/llm-jp-eval", + "project_name": "llm-jp-eval", + "downloads": 564, "source": "Hugging Face", - "score": -0.10413924748379334, - "first_commit": "2023-10-30 07:47:09", - "latest_commit": "2023-12-19 06:43:49", + "score": -0.08681381047376602, + "first_commit": "2024-06-19 10:31:57", + "latest_commit": "2024-08-31 12:40:31", "languages": [], - "model_or_dataset": "model", - "model_size": 6.74, - "model_architectures": "LlamaForCausalLM" + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null }, { - "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", - "url": "https://huggingface.co/tokyotech-llm/Swallow-7b-NVE-hf", - "project_name": "Swallow-7b-NVE-hf", - "downloads": 635, + "description": "bilingual-gpt-neox-4b-instruction-ppo Overview This repository provides an English-Japanese bilingual GPT-NeoX model of 3.8 billion parameters.", + "url": "https://huggingface.co/rinna/bilingual-gpt-neox-4b-instruction-ppo", + "project_name": "bilingual-gpt-neox-4b-instruction-ppo", + "downloads": 563, "source": "Hugging Face", - "score": -0.10446918597437191, - "first_commit": "2023-11-30 09:02:26", - "latest_commit": "2024-06-29 08:56:18", + "score": -0.08682441542430236, + "first_commit": "2023-08-02 05:56:07", + "latest_commit": "2024-07-20 08:05:14", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LlamaForCausalLM" + "model_size": 3.95, + "model_architectures": "GPTNeoXForCausalLM" }, { - "description": "Ninja-v1-gguf Local-Novel-LLM-projectさんが公開しているNinja-v1のggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Ninja-v1-gguf", - "project_name": "Ninja-v1-gguf", - "downloads": 628, + "description": "DataPilot-ArrowPro-7B-KUJIRA-gguf DataPilotさんが公開しているArrowPro-7B-KUJIRAのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/DataPilot-ArrowPro-7B-KUJIRA-gguf", + "project_name": "DataPilot-ArrowPro-7B-KUJIRA-gguf", + "downloads": 560, "source": "Hugging Face", - "score": -0.10457916547123142, - "first_commit": "2024-05-03 14:03:22", - "latest_commit": "2024-05-04 13:26:22", + "score": -0.08685623027591136, + "first_commit": "2024-05-09 13:21:27", + "latest_commit": "2024-05-11 07:24:16", "languages": [], "model_or_dataset": "model", "model_size": 7.24, "model_architectures": null }, { - "description": "Fish Speech V1.2 Fish Speech V1.2 is a leading text-to-speech (TTS) model trained on 300k hours of English, Chinese, and Japanese audio data.", - "url": "https://huggingface.co/fishaudio/fish-speech-1.2", - "project_name": "fish-speech-1.2", - "downloads": 625, + "description": "Sarashina1-7B This repository provides Japanese language models trained by SB Intuitions.", + "url": "https://huggingface.co/sbintuitions/sarashina1-7b", + "project_name": "sarashina1-7b", + "downloads": 560, "source": "Hugging Face", - "score": -0.10462629954131407, - "first_commit": "2024-07-02 04:24:09", - "latest_commit": "2024-07-02 04:31:26", + "score": -0.08685623027591136, + "first_commit": "2024-06-07 10:13:21", + "latest_commit": "2024-06-27 06:55:38", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "GPTNeoXForCausalLM" }, { - "description": "このモデルはluke-japanese-baseをファインチューニングして、固有表現抽出（NER）に用いれるようにしたものです。 ", - "url": "https://huggingface.co/Mizuiro-sakura/luke-japanese-base-finetuned-ner", - "project_name": "luke-japanese-base-finetuned-ner", - "downloads": 623, + "description": "オリジナルのサイトと同じものを使用しています。 ", + "url": "https://huggingface.co/datasets/llm-book/livedoor-news-corpus", + "project_name": "livedoor-news-corpus", + "downloads": 559, "source": "Hugging Face", - "score": -0.1046577222547025, - "first_commit": "2023-01-17 23:36:52", - "latest_commit": "2023-05-12 00:36:17", + "score": -0.08686683522644768, + "first_commit": "2023-06-21 07:16:52", + "latest_commit": "2023-12-12 11:19:43", "languages": [], - "model_or_dataset": "model", - "model_size": 0.279, - "model_architectures": "LukeForTokenClassification" + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null }, { - "description": "rinna/nekomata-14b Overview We conduct continual pre-training of qwen-14b on 66B tokens from a mixture of Japanese and English datasets.", - "url": "https://huggingface.co/rinna/nekomata-14b", - "project_name": "nekomata-14b", - "downloads": 619, + "description": "ELYZA-japanese-Llama-2-7b-fast-gguf ELYZAさんが公開しているELYZA-japanese-Llama-2-7b-fastのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-7b-fast-gguf", + "project_name": "ELYZA-japanese-Llama-2-7b-fast-gguf", + "downloads": 557, "source": "Hugging Face", - "score": -0.10472056768147937, - "first_commit": "2023-12-19 08:09:53", - "latest_commit": "2024-07-22 07:58:40", + "score": -0.08688804512752035, + "first_commit": "2023-08-29 07:23:20", + "latest_commit": "2023-11-16 14:27:36", "languages": [], "model_or_dataset": "model", - "model_size": 14.2, - "model_architectures": "QWenLMHeadModel" + "model_size": 6.85, + "model_architectures": null }, { - "description": "このモデルは何？ ", - "url": "https://huggingface.co/Lasorco/lametta", - "project_name": "lametta", - "downloads": 619, + "description": "Japanese-StableLM-Base-JAVocab-Beta-7B A cute robot wearing a kimono writes calligraphy with one single brush — Stable Diffusion XL Model Description japanese-stablelm-base-ja_vocab-beta-7b is a 7B-parameter decoder-only language model based on Llama-2-7b that has been fine-tuned on a diverse collection of Japanese data, with the intent of maximizing downstream performance on Japanese language tasks.", + "url": "https://huggingface.co/stabilityai/japanese-stablelm-base-ja_vocab-beta-7b", + "project_name": "japanese-stablelm-base-ja_vocab-beta-7b", + "downloads": 555, "source": "Hugging Face", - "score": -0.10472056768147937, - "first_commit": "2023-03-28 14:29:55", - "latest_commit": "2023-11-08 07:37:12", + "score": -0.08690925502859302, + "first_commit": "2023-10-30 07:49:15", + "latest_commit": "2023-12-19 06:45:58", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": null + "model_size": 6.88, + "model_architectures": "LlamaForCausalLM" }, { - "description": "Chat & support: TheBloke's Discord server Want to contribute?", - "url": "https://huggingface.co/TheBloke/japanese-stablelm-instruct-beta-70B-GGUF", - "project_name": "japanese-stablelm-instruct-beta-70B-GGUF", - "downloads": 614, + "description": "Qwen1.5-110B-Chat-gguf Qwenさんが公開しているQwen1.5-110B-Chatのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Qwen1.5-110B-Chat-gguf", + "project_name": "Qwen1.5-110B-Chat-gguf", + "downloads": 554, "source": "Hugging Face", - "score": -0.10479912446495046, - "first_commit": "2023-11-02 15:45:24", - "latest_commit": "2023-11-02 18:22:05", + "score": -0.08691985997912936, + "first_commit": "2024-04-27 19:35:48", + "latest_commit": "2024-04-28 08:09:17", "languages": [], "model_or_dataset": "model", - "model_size": 69.0, + "model_size": 111.0, "model_architectures": null }, { - "description": "rinna-llama-3-youko-8b-gguf rinnaさんが公開しているllama-3-youko-8bのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/rinna-llama-3-youko-8b-gguf", - "project_name": "rinna-llama-3-youko-8b-gguf", - "downloads": 612, + "description": "bilingual-gpt-neox-4b-8k Overview Notice: This model requires transformers>=4.31.0 to work properly.", + "url": "https://huggingface.co/rinna/bilingual-gpt-neox-4b-8k", + "project_name": "bilingual-gpt-neox-4b-8k", + "downloads": 554, "source": "Hugging Face", - "score": -0.1048305471783389, - "first_commit": "2024-05-01 14:17:53", - "latest_commit": "2024-05-01 15:11:21", + "score": -0.08691985997912936, + "first_commit": "2023-07-31 02:34:21", + "latest_commit": "2024-07-20 08:03:16", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": null + "model_size": 3.95, + "model_architectures": "GPTNeoXForCausalLM" }, { "description": "KARAKURI LM KARAKURI LM is a pretrained language model that builds upon Llama 2.", - "url": "https://huggingface.co/karakuri-ai/karakuri-lm-70b-v0.1", - "project_name": "karakuri-lm-70b-v0.1", - "downloads": 609, + "url": "https://huggingface.co/karakuri-ai/karakuri-lm-70b-chat-v0.1", + "project_name": "karakuri-lm-70b-chat-v0.1", + "downloads": 550, "source": "Hugging Face", - "score": -0.10487768124842155, - "first_commit": "2024-01-26 10:49:53", - "latest_commit": "2024-05-07 09:00:06", + "score": -0.0869622797812747, + "first_commit": "2024-01-26 09:08:09", + "latest_commit": "2024-05-07 09:00:17", "languages": [], "model_or_dataset": "model", "model_size": 69.2, "model_architectures": "LlamaForCausalLM" }, { - "description": "llm-jp-13b-instruct-lora-jaster-dolly-oasst-v1.0", - "url": "https://huggingface.co/llm-jp/llm-jp-13b-instruct-lora-jaster-dolly-oasst-v1.0", - "project_name": "llm-jp-13b-instruct-lora-jaster-dolly-oasst-v1.0", - "downloads": 606, + "description": "Sarashina1-65B", + "url": "https://huggingface.co/sbintuitions/sarashina1-65b", + "project_name": "sarashina1-65b", + "downloads": 546, "source": "Hugging Face", - "score": -0.1049248153185042, - "first_commit": "2023-10-18 19:01:48", - "latest_commit": "2023-10-20 08:41:17", + "score": -0.08700469958342003, + "first_commit": "2024-06-07 11:57:56", + "latest_commit": "2024-06-27 06:56:36", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": null - }, - { - "description": "japanese-gpt-neox-3.6b-instruction-sft-v2 Overview", - "url": "https://huggingface.co/rinna/japanese-gpt-neox-3.6b-instruction-sft-v2", - "project_name": "japanese-gpt-neox-3.6b-instruction-sft-v2", - "downloads": 593, - "source": "Hugging Face", - "score": -0.10512906295552903, - "first_commit": "2023-05-30 01:50:25", - "latest_commit": "2024-07-20 07:57:35", - "languages": [], - "model_or_dataset": "model", - "model_size": 3.76, "model_architectures": "GPTNeoXForCausalLM" }, { - "description": "alabnii/jmedroberta-base-manbyo-wordpiece Model description This is a Japanese RoBERTa base model pre-trained on academic articles in medical sciences collected by Japan Science and Technology Agency (JST).", - "url": "https://huggingface.co/alabnii/jmedroberta-base-manbyo-wordpiece", - "project_name": "jmedroberta-base-manbyo-wordpiece", - "downloads": 589, + "description": "DeBERTa V2 base Japanese This is a DeBERTaV2 model pretrained on Japanese texts.", + "url": "https://huggingface.co/izumi-lab/deberta-v2-base-japanese", + "project_name": "deberta-v2-base-japanese", + "downloads": 542, "source": "Hugging Face", - "score": -0.10519190838230588, - "first_commit": "2022-12-22 17:17:03", - "latest_commit": "2023-03-08 01:44:36", + "score": -0.08704711938556536, + "first_commit": "2023-10-21 13:24:11", + "latest_commit": "2024-07-19 03:07:57", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "BertForMaskedLM" + "model_architectures": "DebertaV2ForMaskedLM" }, { - "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", - "url": "https://huggingface.co/tokyotech-llm/Swallow-70b-NVE-hf", - "project_name": "Swallow-70b-NVE-hf", - "downloads": 586, + "description": "Japanese CLIP ViT-H/14 (Wider) Table of Contents Overview Usage Model Details Evaluation Limitations and Biases Citation See Also Contact Information Overview Developed by:", + "url": "https://huggingface.co/hakuhodo-tech/japanese-clip-vit-h-14-bert-wider", + "project_name": "japanese-clip-vit-h-14-bert-wider", + "downloads": 540, "source": "Hugging Face", - "score": -0.10523904245238853, - "first_commit": "2023-12-07 07:34:35", - "latest_commit": "2024-06-29 08:56:25", + "score": -0.08706832928663803, + "first_commit": "2024-03-06 03:30:25", + "latest_commit": "2024-03-06 21:46:11", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LlamaForCausalLM" + "model_size": 0.91, + "model_architectures": "CustomCLIPModel" }, { - "description": "bilingual-gpt-neox-4b-instruction-ppo Overview This repository provides an English-Japanese bilingual GPT-NeoX model of 3.8 billion parameters.", - "url": "https://huggingface.co/rinna/bilingual-gpt-neox-4b-instruction-ppo", - "project_name": "bilingual-gpt-neox-4b-instruction-ppo", - "downloads": 585, + "description": "(简体中文|English|日本語) Introduction github repo : https://github.com/FunAudioLLM/SenseVoice SenseVoice is a speech foundation model with multiple speech understanding capabilities, including automatic speech recognition (ASR), spoken language identification (LID), speech emotion recognition (SER), and audio event detection (AED).", + "url": "https://huggingface.co/FunAudioLLM/SenseVoiceSmall", + "project_name": "SenseVoiceSmall", + "downloads": 539, "source": "Hugging Face", - "score": -0.10525475380908275, - "first_commit": "2023-08-02 05:56:07", - "latest_commit": "2024-07-20 08:05:14", + "score": -0.08707893423717437, + "first_commit": "2024-07-03 03:56:49", + "latest_commit": "2024-07-31 05:47:48", "languages": [], "model_or_dataset": "model", - "model_size": 3.95, - "model_architectures": "GPTNeoXForCausalLM" + "model_size": null, + "model_architectures": null }, { - "description": "PLaMo-13B-Instruct-NC Model Description PLaMo-13B-Instruct-NC is a noncommercial instruct fine-tuned model built upon the 8192 context length version of PLaMo-13B text generation model.", - "url": "https://huggingface.co/pfnet/plamo-13b-instruct-nc", - "project_name": "plamo-13b-instruct-nc", - "downloads": 578, + "description": "aixsatoshi-Llama-3-8b-Cosmopedia-japanese-gguf aixsatoshiさんが公開しているLlama-3-8b-Cosmopedia-japaneseのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/aixsatoshi-Llama-3-8b-Cosmopedia-japanese-gguf", + "project_name": "aixsatoshi-Llama-3-8b-Cosmopedia-japanese-gguf", + "downloads": 536, "source": "Hugging Face", - "score": -0.10536473330594227, - "first_commit": "2023-10-26 05:36:26", - "latest_commit": "2024-01-25 07:46:45", + "score": -0.08711074908878337, + "first_commit": "2024-05-01 12:36:43", + "latest_commit": "2024-05-19 08:27:21", "languages": [], "model_or_dataset": "model", - "model_size": 13.1, - "model_architectures": "PlamoForCausalLM" + "model_size": 8.03, + "model_architectures": null }, { - "description": "albert-base-japanese-v1 日本語事前学習済みALBERTモデルです How to use ファインチューニング このモデルはPreTrainedモデルです基本的には各種タスク用にファインチューニングして使用されることを想定しています Fill-Mask このモデルではTokenizerにSentencepieceを利用していますそのままでは[MASK]トークンのあとに余計なトークンが混入する問題があるので、利用する際には以下のようにする必要があります for PyTorch from transformers import ( AlbertForMaskedLM, AlbertTokenizerFast ) import torch tokenizer = AlbertTokenizerFast.from_pretrained(\"ken11/albert-base-japanese-v1\")", - "url": "https://huggingface.co/ken11/albert-base-japanese-v1", - "project_name": "albert-base-japanese-v1", - "downloads": 567, + "description": "Model Card for Japanese character-level DeBERTa V2 tiny Model description This is a Japanese DeBERTa V2 tiny model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.", + "url": "https://huggingface.co/ku-nlp/deberta-v2-tiny-japanese-char-wwm", + "project_name": "deberta-v2-tiny-japanese-char-wwm", + "downloads": 534, "source": "Hugging Face", - "score": -0.10553755822957867, - "first_commit": "2021-12-19 17:07:14", - "latest_commit": "2021-12-22 03:04:30", + "score": -0.08713195898985604, + "first_commit": "2023-01-05 08:48:29", + "latest_commit": "2023-03-23 07:31:19", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "AlbertForMaskedLM" + "model_size": 0.0101, + "model_architectures": "DebertaV2ForMaskedLM" }, { - "description": "japanese-large-lm-1.7b-instruction-sft This repository provides a 1.7B parameters Japanese language model, fine-tuned and trained by LINE Corporation.", - "url": "https://huggingface.co/line-corporation/japanese-large-lm-1.7b-instruction-sft", - "project_name": "japanese-large-lm-1.7b-instruction-sft", - "downloads": 563, + "description": "bert-base-japanese-v3-jnli 「大規模言語モデル入門」の第5章で紹介している(自然言語推論)のモデルです。 ", + "url": "https://huggingface.co/llm-book/bert-base-japanese-v3-jnli", + "project_name": "bert-base-japanese-v3-jnli", + "downloads": 527, "source": "Hugging Face", - "score": -0.10560040365635553, - "first_commit": "2023-08-14 17:19:11", - "latest_commit": "2023-08-14 17:19:11", + "score": -0.08720619364361037, + "first_commit": "2023-06-12 14:15:16", + "latest_commit": "2023-07-24 06:49:14", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "GPT2LMHeadModel" + "model_architectures": "BertForSequenceClassification" }, { - "description": "Sarashina1-7B This repository provides Japanese language models trained by SB Intuitions.", - "url": "https://huggingface.co/sbintuitions/sarashina1-7b", - "project_name": "sarashina1-7b", - "downloads": 551, + "description": "hotchpotch/japanese-bge-reranker-v2-m3-v1 日本語で学習させた Reranker (CrossEncoder) シリーズです。 ", + "url": "https://huggingface.co/hotchpotch/japanese-bge-reranker-v2-m3-v1", + "project_name": "japanese-bge-reranker-v2-m3-v1", + "downloads": 518, "source": "Hugging Face", - "score": -0.10578893993668614, - "first_commit": "2024-06-07 10:13:21", - "latest_commit": "2024-06-27 06:55:38", + "score": -0.08730163819843738, + "first_commit": "2024-03-28 20:45:16", + "latest_commit": "2024-04-01 02:40:22", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "GPTNeoXForCausalLM" + "model_size": 0.5680000000000001, + "model_architectures": "XLMRobertaForSequenceClassification" }, { - "description": "Japanese-StableLM-Base-JAVocab-Beta-7B A cute robot wearing a kimono writes calligraphy with one single brush — Stable Diffusion XL Model Description japanese-stablelm-base-ja_vocab-beta-7b is a 7B-parameter decoder-only language model based on Llama-2-7b that has been fine-tuned on a diverse collection of Japanese data, with the intent of maximizing downstream performance on Japanese language tasks.", - "url": "https://huggingface.co/stabilityai/japanese-stablelm-base-ja_vocab-beta-7b", - "project_name": "japanese-stablelm-base-ja_vocab-beta-7b", - "downloads": 546, + "description": "読み込み方 from datasets import load_dataset dataset = load_dataset(\"YANS-official/senryu-shashin\", split=\"train\") 概要 株式会社東建コーポレーションが運営するホームメイト・リサーチによる『ホームメイト川柳大賞』のうち、お題が画像形式で提供される『写真川柳』に関するクロールデータです。", + "url": "https://huggingface.co/datasets/YANS-official/senryu-shashin", + "project_name": "senryu-shashin", + "downloads": 507, "source": "Hugging Face", - "score": -0.10586749672015722, - "first_commit": "2023-10-30 07:49:15", - "latest_commit": "2023-12-19 06:45:58", + "score": -0.08741829265433705, + "first_commit": "2024-08-28 18:50:08", + "latest_commit": "2024-08-31 03:47:50", "languages": [], - "model_or_dataset": "model", - "model_size": 6.88, - "model_architectures": "LlamaForCausalLM" + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null }, { - "description": "karakuri-lm-70b-chat-v0.1-gguf karakuri-aiさんが公開しているkarakuri-lm-70b-chat-v0.1のggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/karakuri-lm-70b-chat-v0.1-gguf", - "project_name": "karakuri-lm-70b-chat-v0.1-gguf", - "downloads": 545, + "description": "HODACHI-EZO-Common-T2-2B-gemma-2-it-gguf HODACHIさんが公開しているEZO-Common-T2-2B-gemma-2-itのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/HODACHI-EZO-Common-T2-2B-gemma-2-it-gguf", + "project_name": "HODACHI-EZO-Common-T2-2B-gemma-2-it-gguf", + "downloads": 502, "source": "Hugging Face", - "score": -0.10588320807685143, - "first_commit": "2024-02-01 10:42:18", - "latest_commit": "2024-05-09 15:22:45", + "score": -0.08747131740701872, + "first_commit": "2024-08-01 17:32:31", + "latest_commit": "2024-08-01 18:38:31", "languages": [], "model_or_dataset": "model", - "model_size": 69.2, + "model_size": 2.61, "model_architectures": null }, { - "description": "bert-base-japanese-v3-jnli 「大規模言語モデル入門」の第5章で紹介している(自然言語推論)のモデルです。 ", - "url": "https://huggingface.co/llm-book/bert-base-japanese-v3-jnli", - "project_name": "bert-base-japanese-v3-jnli", - "downloads": 545, + "description": "ku-nlp/roberta-base-japanese-char-wwm Model description This is a Japanese RoBERTa base model pre-trained on Japanese Wikipedia and the Japanese portion of CC-100.", + "url": "https://huggingface.co/ku-nlp/roberta-base-japanese-char-wwm", + "project_name": "roberta-base-japanese-char-wwm", + "downloads": 501, "source": "Hugging Face", - "score": -0.10588320807685143, - "first_commit": "2023-06-12 14:15:16", - "latest_commit": "2023-07-24 06:49:14", + "score": -0.08748192235755506, + "first_commit": "2022-09-20 05:07:34", + "latest_commit": "2023-03-20 08:05:45", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForSequenceClassification" + "model_size": 0.1, + "model_architectures": "RobertaForMaskedLM" }, { - "description": "※llama.cpp Releases b3428(7/21)", - "url": "https://huggingface.co/MCZK/EZO-Common-9B-gemma-2-it-GGUF", - "project_name": "EZO-Common-9B-gemma-2-it-GGUF", - "downloads": 542, + "description": "stockmark-gpt-neox-japanese-1.4b-gguf stockmarkさんが公開しているgpt-neox-japanese-1.4bのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/stockmark-gpt-neox-japanese-1.4b-gguf", + "project_name": "stockmark-gpt-neox-japanese-1.4b-gguf", + "downloads": 496, "source": "Hugging Face", - "score": -0.10593034214693409, - "first_commit": "2024-07-10 11:12:59", - "latest_commit": "2024-07-21 11:26:08", + "score": -0.08753494711023672, + "first_commit": "2023-08-22 12:45:18", + "latest_commit": "2023-09-08 22:00:37", "languages": [], "model_or_dataset": "model", - "model_size": 9.24, + "model_size": 1.41, "model_architectures": null }, - { - "description": "KARAKURI LM KARAKURI LM is a pretrained language model that builds upon Llama 2.", - "url": "https://huggingface.co/karakuri-ai/karakuri-lm-70b-chat-v0.1", - "project_name": "karakuri-lm-70b-chat-v0.1", - "downloads": 541, - "source": "Hugging Face", - "score": -0.1059460535036283, - "first_commit": "2024-01-26 09:08:09", - "latest_commit": "2024-05-07 09:00:17", - "languages": [], - "model_or_dataset": "model", - "model_size": 69.2, - "model_architectures": "LlamaForCausalLM" - }, { "description": "ELYZA-japanese-Llama-2-7b-gguf ELYZAさんが公開しているELYZA-japanese-Llama-2-7bのggufフォーマット変換版です。 ", "url": "https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-7b-gguf", "project_name": "ELYZA-japanese-Llama-2-7b-gguf", - "downloads": 532, + "downloads": 495, "source": "Hugging Face", - "score": -0.10608745571387626, + "score": -0.08754555206077305, "first_commit": "2023-08-29 06:32:01", "latest_commit": "2023-11-16 14:27:12", "languages": [], @@ -5659,362 +5707,348 @@ "model_architectures": null }, { - "description": "Tanuki-8B-dpo-v1.0-GGUF 概要 GENIAC 松尾研 LLM開発プロジェクトで開発されたLLMであるweblab-GENIAC/Tanuki-8B-dpo-v1.0のGGUF量子化モデルです。", - "url": "https://huggingface.co/team-hatakeyama-phase2/Tanuki-8B-dpo-v1.0-GGUF", - "project_name": "Tanuki-8B-dpo-v1.0-GGUF", - "downloads": 530, + "description": "alabnii/jmedroberta-base-manbyo-wordpiece Model description This is a Japanese RoBERTa base model pre-trained on academic articles in medical sciences collected by Japan Science and Technology Agency (JST).", + "url": "https://huggingface.co/alabnii/jmedroberta-base-manbyo-wordpiece", + "project_name": "jmedroberta-base-manbyo-wordpiece", + "downloads": 494, "source": "Hugging Face", - "score": -0.1061188784272647, - "first_commit": "2024-08-14 15:05:50", - "latest_commit": "2024-08-27 18:00:44", + "score": -0.0875561570113094, + "first_commit": "2022-12-22 17:17:03", + "latest_commit": "2023-03-08 01:44:36", "languages": [], "model_or_dataset": "model", - "model_size": 7.51, - "model_architectures": null + "model_size": null, + "model_architectures": "BertForMaskedLM" }, { - "description": "stockmark-gpt-neox-japanese-1.4b-gguf stockmarkさんが公開しているgpt-neox-japanese-1.4bのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/stockmark-gpt-neox-japanese-1.4b-gguf", - "project_name": "stockmark-gpt-neox-japanese-1.4b-gguf", - "downloads": 528, + "description": "Japanese-StableLM-Instruct-JAVocab-Beta-7B A cute robot wearing a kimono writes calligraphy with one single brush — Stable Diffusion XL Model Description japanese-stablelm-instruct-ja_vocab-beta-7b is a 7B-parameter decoder-only language model based on japanese-stablelm-ja_vocab-beta-7b and further fine tuned on Databricks Dolly-15k, Anthropic HH, and other public data.", + "url": "https://huggingface.co/stabilityai/japanese-stablelm-instruct-ja_vocab-beta-7b", + "project_name": "japanese-stablelm-instruct-ja_vocab-beta-7b", + "downloads": 482, "source": "Hugging Face", - "score": -0.10615030114065313, - "first_commit": "2023-08-22 12:45:18", - "latest_commit": "2023-09-08 22:00:37", + "score": -0.0876834164177454, + "first_commit": "2023-10-30 07:49:38", + "latest_commit": "2023-12-19 06:46:01", "languages": [], "model_or_dataset": "model", - "model_size": 1.41, - "model_architectures": null + "model_size": 6.88, + "model_architectures": "LlamaForCausalLM" }, { - "description": "ichikara-instruction (Non Commercial) LLMのための日本語インストラクションデータ 公開ページ 公開ページより、 本データに関して、言語処理学会第３０回年次大会において発表を行います。", - "url": "https://huggingface.co/datasets/p1atdev/ichikara-instruction", - "project_name": "ichikara-instruction", - "downloads": 528, + "description": "To load a language pair which isn't part of the config, all you need to do is specify the language code as pairs.", + "url": "https://huggingface.co/datasets/Helsinki-NLP/tatoeba", + "project_name": "tatoeba", + "downloads": 479, "source": "Hugging Face", - "score": -0.10615030114065313, - "first_commit": "2024-03-12 07:09:56", - "latest_commit": "2024-03-12 08:36:40", + "score": -0.0877152312693544, + "first_commit": "2022-01-25 16:36:30", + "latest_commit": "2024-01-18 11:16:48", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "Sarashina1-65B", - "url": "https://huggingface.co/sbintuitions/sarashina1-65b", - "project_name": "sarashina1-65b", - "downloads": 525, + "description": "Japanese StableLM-3B-4E1T Base Model Description This is a 3B-parameter decoder-only language model with a focus on maximizing Japanese language modeling performance and Japanese downstream task performance.", + "url": "https://huggingface.co/stabilityai/japanese-stablelm-3b-4e1t-base", + "project_name": "japanese-stablelm-3b-4e1t-base", + "downloads": 478, "source": "Hugging Face", - "score": -0.10619743521073578, - "first_commit": "2024-06-07 11:57:56", - "latest_commit": "2024-06-27 06:56:36", + "score": -0.08772583621989073, + "first_commit": "2023-10-16 06:04:58", + "latest_commit": "2024-04-26 03:20:34", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "GPTNeoXForCausalLM" + "model_size": 2.8, + "model_architectures": "StableLMEpochForCausalLM" }, { - "description": "DataPilot-ArrowPro-7B-KUJIRA-gguf DataPilotさんが公開しているArrowPro-7B-KUJIRAのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/DataPilot-ArrowPro-7B-KUJIRA-gguf", - "project_name": "DataPilot-ArrowPro-7B-KUJIRA-gguf", - "downloads": 523, + "description": "This repository contains some GGUF quantizations of the merge of the VNTL LLaMA 3 8B qlora.", + "url": "https://huggingface.co/lmg-anon/vntl-llama3-8b-gguf", + "project_name": "vntl-llama3-8b-gguf", + "downloads": 477, "source": "Hugging Face", - "score": -0.10622885792412422, - "first_commit": "2024-05-09 13:21:27", - "latest_commit": "2024-05-11 07:24:16", + "score": -0.08773644117042706, + "first_commit": "2024-06-13 17:17:30", + "latest_commit": "2024-06-15 17:33:02", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, + "model_size": 8.03, "model_architectures": null }, { - "description": "aixsatoshi-Llama-3-8b-Cosmopedia-japanese-gguf aixsatoshiさんが公開しているLlama-3-8b-Cosmopedia-japaneseのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/aixsatoshi-Llama-3-8b-Cosmopedia-japanese-gguf", - "project_name": "aixsatoshi-Llama-3-8b-Cosmopedia-japanese-gguf", - "downloads": 518, + "description": "japanese-gpt-neox-small This repository provides a small-sized Japanese GPT-NeoX model.", + "url": "https://huggingface.co/rinna/japanese-gpt-neox-small", + "project_name": "japanese-gpt-neox-small", + "downloads": 477, "source": "Hugging Face", - "score": -0.1063074147075953, - "first_commit": "2024-05-01 12:36:43", - "latest_commit": "2024-05-19 08:27:21", + "score": -0.08773644117042706, + "first_commit": "2022-08-31 05:58:25", + "latest_commit": "2024-07-20 07:53:40", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": null + "model_size": 0.20400000000000001, + "model_architectures": "GPTNeoXForCausalLM" }, { - "description": "ELYZA-japanese-Llama-2-13b-fast-gguf ELYZAさんが公開しているELYZA-japanese-Llama-2-13b-fastのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-13b-fast-gguf", - "project_name": "ELYZA-japanese-Llama-2-13b-fast-gguf", - "downloads": 512, + "description": "This repository is publicly accessible, but you have to accept the conditions to access its files and content.", + "url": "https://huggingface.co/stabilityai/japanese-stablelm-instruct-alpha-7b", + "project_name": "japanese-stablelm-instruct-alpha-7b", + "downloads": 473, "source": "Hugging Face", - "score": -0.10640168284776061, - "first_commit": "2023-12-27 10:40:52", - "latest_commit": "2023-12-27 13:18:46", + "score": -0.0877788609725724, + "first_commit": null, + "latest_commit": null, "languages": [], "model_or_dataset": "model", - "model_size": 13.1, - "model_architectures": null - }, - { - "description": "オリジナルのサイトと同じものを使用しています。 ", - "url": "https://huggingface.co/datasets/llm-book/livedoor-news-corpus", - "project_name": "livedoor-news-corpus", - "downloads": 510, - "source": "Hugging Face", - "score": -0.10643310556114904, - "first_commit": "2023-06-21 07:16:52", - "latest_commit": "2023-12-12 11:19:43", - "languages": [], - "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "To load a language pair which isn't part of the config, all you need to do is specify the language code as pairs.", - "url": "https://huggingface.co/datasets/Helsinki-NLP/tatoeba", - "project_name": "tatoeba", - "downloads": 504, + "description": "Japanese-Starling-ChatV-7B-GGUF GGUF conversion of \"Japanese-Starling-ChatV-7B\" \"Japanese-Starling-ChatV-7B\" is a Japanese chat model built on top of \"chatntq-ja-7b-v1.0\", originally based on Mistral-7B-v0.1.", + "url": "https://huggingface.co/TFMC/Japanese-Starling-ChatV-7B-GGUF", + "project_name": "Japanese-Starling-ChatV-7B-GGUF", + "downloads": 473, "source": "Hugging Face", - "score": -0.10652737370131435, - "first_commit": "2022-01-25 16:36:30", - "latest_commit": "2024-01-18 11:16:48", + "score": -0.0877788609725724, + "first_commit": "2024-04-14 12:42:01", + "latest_commit": "2024-04-20 01:23:10", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_or_dataset": "model", + "model_size": 7.24, "model_architectures": null }, { - "description": "Tanuki-8x8B-dpo-v1.0-GGUF 概要 GENIAC 松尾研 LLM開発プロジェクトで開発されたLLMであるweblab-GENIAC/Tanuki-8x8B-dpo-v1.0のGGUF量子化モデルです。", - "url": "https://huggingface.co/team-hatakeyama-phase2/Tanuki-8x8B-dpo-v1.0-GGUF", - "project_name": "Tanuki-8x8B-dpo-v1.0-GGUF", - "downloads": 496, + "description": "このモデルはluke-japanese-baseをファインチューニングして、固有表現抽出（NER）に用いれるようにしたものです。 ", + "url": "https://huggingface.co/Mizuiro-sakura/luke-japanese-base-finetuned-ner", + "project_name": "luke-japanese-base-finetuned-ner", + "downloads": 471, "source": "Hugging Face", - "score": -0.10665306455486807, - "first_commit": "2024-08-14 18:48:45", - "latest_commit": "2024-08-29 17:42:37", + "score": -0.08780007087364507, + "first_commit": "2023-01-17 23:36:52", + "latest_commit": "2023-05-12 00:36:17", "languages": [], "model_or_dataset": "model", - "model_size": 47.0, - "model_architectures": null + "model_size": 0.279, + "model_architectures": "LukeForTokenClassification" }, { - "description": "This is a Japanese translated version of HumanEval, an evaluation harness for the HumanEval problem solving dataset described in the paper \"Evaluating Large Language Models Trained on Code\".", - "url": "https://huggingface.co/datasets/kogi-jwu/jhumaneval", - "project_name": "jhumaneval", - "downloads": 494, + "description": "Llama-3.1-70B-EZO-1.1-it-gguf HODACHIさんが公開しているLlama-3.1-70B-EZO-1.1-itのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Llama-3.1-70B-EZO-1.1-it-gguf", + "project_name": "Llama-3.1-70B-EZO-1.1-it-gguf", + "downloads": 465, "source": "Hugging Face", - "score": -0.10668448726825651, - "first_commit": "2023-10-21 08:20:14", - "latest_commit": "2024-01-10 21:52:35", + "score": -0.08786370057686307, + "first_commit": "2024-07-31 12:12:13", + "latest_commit": "2024-07-31 21:47:25", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_or_dataset": "model", + "model_size": 70.6, "model_architectures": null }, { - "description": "Japanese StableLM-3B-4E1T Base Model Description This is a 3B-parameter decoder-only language model with a focus on maximizing Japanese language modeling performance and Japanese downstream task performance.", - "url": "https://huggingface.co/stabilityai/japanese-stablelm-3b-4e1t-base", - "project_name": "japanese-stablelm-3b-4e1t-base", - "downloads": 492, + "description": "umiyuki-Umievo-itr012-Gleipnir-7B-gguf umiyukiさんが公開しているUmievo-itr012-Gleipnir-7Bのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/umiyuki-Umievo-itr012-Gleipnir-7B-gguf", + "project_name": "umiyuki-Umievo-itr012-Gleipnir-7B-gguf", + "downloads": 461, "source": "Hugging Face", - "score": -0.10671590998164494, - "first_commit": "2023-10-16 06:04:58", - "latest_commit": "2024-04-26 03:20:34", + "score": -0.08790612037900841, + "first_commit": "2024-05-29 15:05:32", + "latest_commit": "2024-05-29 15:53:40", "languages": [], "model_or_dataset": "model", - "model_size": 2.8, - "model_architectures": "StableLMEpochForCausalLM" + "model_size": 7.24, + "model_architectures": null }, { - "description": "japanese-gpt-neox-small This repository provides a small-sized Japanese GPT-NeoX model.", - "url": "https://huggingface.co/rinna/japanese-gpt-neox-small", - "project_name": "japanese-gpt-neox-small", - "downloads": 484, + "description": "This is a model for named entity recognition of Japanese medical documents.", + "url": "https://huggingface.co/sociocom/MedNER-CR-JA", + "project_name": "MedNER-CR-JA", + "downloads": 460, "source": "Hugging Face", - "score": -0.10684160083519868, - "first_commit": "2022-08-31 05:58:25", - "latest_commit": "2024-07-20 07:53:40", + "score": -0.08791672532954474, + "first_commit": "2022-08-23 03:30:43", + "latest_commit": "2024-07-31 07:44:00", "languages": [], "model_or_dataset": "model", - "model_size": 0.20400000000000001, - "model_architectures": "GPTNeoXForCausalLM" + "model_size": 0.11, + "model_architectures": "BertForTokenClassification" }, { - "description": "bert-base-japanese-v3-unsup-simcse-jawiki 「大規模言語モデル入門」の第8章で紹介している教師なしSimCSEのモデルです。 ", - "url": "https://huggingface.co/llm-book/bert-base-japanese-v3-unsup-simcse-jawiki", - "project_name": "bert-base-japanese-v3-unsup-simcse-jawiki", - "downloads": 483, + "description": "Sarashina1-13B", + "url": "https://huggingface.co/sbintuitions/sarashina1-13b", + "project_name": "sarashina1-13b", + "downloads": 460, "source": "Hugging Face", - "score": -0.1068573121918929, - "first_commit": "2023-06-21 10:52:27", - "latest_commit": "2023-07-24 07:07:44", + "score": -0.08791672532954474, + "first_commit": "2024-06-07 11:56:53", + "latest_commit": "2024-06-27 06:56:06", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "BertModel" + "model_architectures": "GPTNeoXForCausalLM" }, { - "description": "Mistral-Nemo-Instruct-2407-gguf mistralaiさんが公開しているMistral-Nemo-Instruct-2407のggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Mistral-Nemo-Instruct-2407-gguf", - "project_name": "Mistral-Nemo-Instruct-2407-gguf", - "downloads": 470, + "description": "Overview This dataset provides a convenient and user-friendly format of data from Aozora Bunko (青空文庫), a website that compiles public-domain books in Japan, ideal for Machine Learning applications.", + "url": "https://huggingface.co/datasets/globis-university/aozorabunko-clean", + "project_name": "aozorabunko-clean", + "downloads": 458, "source": "Hugging Face", - "score": -0.10706155982891773, - "first_commit": "2024-07-22 13:28:13", - "latest_commit": "2024-07-22 17:25:48", + "score": -0.08793793523061741, + "first_commit": "2023-06-26 13:31:28", + "latest_commit": "2023-10-27 13:22:32", "languages": [], - "model_or_dataset": "model", - "model_size": 12.2, + "model_or_dataset": "dataset", + "model_size": null, "model_architectures": null }, { - "description": "Japanese-Starling-ChatV-7B-GGUF GGUF conversion of \"Japanese-Starling-ChatV-7B\" \"Japanese-Starling-ChatV-7B\" is a Japanese chat model built on top of \"chatntq-ja-7b-v1.0\", originally based on Mistral-7B-v0.1.", - "url": "https://huggingface.co/TFMC/Japanese-Starling-ChatV-7B-GGUF", - "project_name": "Japanese-Starling-ChatV-7B-GGUF", - "downloads": 470, + "description": "luke-japanese luke-japanese is the Japanese version of LUKE (Language Understanding with Knowledge-based Embeddings), a pre-trained knowledge-enhanced contextualized representation of words and entities.", + "url": "https://huggingface.co/studio-ousia/luke-japanese-base", + "project_name": "luke-japanese-base", + "downloads": 455, "source": "Hugging Face", - "score": -0.10706155982891773, - "first_commit": "2024-04-14 12:42:01", - "latest_commit": "2024-04-20 01:23:10", + "score": -0.0879697500822264, + "first_commit": "2022-10-25 06:30:23", + "latest_commit": "2022-11-09 15:23:20", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": null + "model_size": null, + "model_architectures": "LukeForMaskedLM" }, { - "description": "Sarashina1-13B", - "url": "https://huggingface.co/sbintuitions/sarashina1-13b", - "project_name": "sarashina1-13b", - "downloads": 462, + "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", + "url": "https://huggingface.co/tokyotech-llm/Swallow-13b-NVE-hf", + "project_name": "Swallow-13b-NVE-hf", + "downloads": 453, "source": "Hugging Face", - "score": -0.10718725068247147, - "first_commit": "2024-06-07 11:56:53", - "latest_commit": "2024-06-27 06:56:06", + "score": -0.08799095998329907, + "first_commit": "2024-01-30 11:39:05", + "latest_commit": "2024-06-29 08:56:22", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "GPTNeoXForCausalLM" + "model_architectures": "LlamaForCausalLM" }, { - "description": "Japanese-StableLM-Instruct-JAVocab-Beta-7B A cute robot wearing a kimono writes calligraphy with one single brush — Stable Diffusion XL Model Description japanese-stablelm-instruct-ja_vocab-beta-7b is a 7B-parameter decoder-only language model based on japanese-stablelm-ja_vocab-beta-7b and further fine tuned on Databricks Dolly-15k, Anthropic HH, and other public data.", - "url": "https://huggingface.co/stabilityai/japanese-stablelm-instruct-ja_vocab-beta-7b", - "project_name": "japanese-stablelm-instruct-ja_vocab-beta-7b", - "downloads": 462, + "description": "Fish Speech V1.2 Fish Speech V1.2 is a leading text-to-speech (TTS) model trained on 300k hours of English, Chinese, and Japanese audio data.", + "url": "https://huggingface.co/fishaudio/fish-speech-1.2", + "project_name": "fish-speech-1.2", + "downloads": 449, "source": "Hugging Face", - "score": -0.10718725068247147, - "first_commit": "2023-10-30 07:49:38", - "latest_commit": "2023-12-19 06:46:01", + "score": -0.08803337978544441, + "first_commit": "2024-07-02 04:24:09", + "latest_commit": "2024-07-02 04:31:26", "languages": [], "model_or_dataset": "model", - "model_size": 6.88, - "model_architectures": "LlamaForCausalLM" + "model_size": null, + "model_architectures": null }, { - "description": "HODACHI様の Llama-3.1-8B-EZO-1.1-it をGGUF形式に変換したものです。 ", - "url": "https://huggingface.co/MCZK/Llama-3.1-8B-EZO-1.1-it-GGUF", - "project_name": "Llama-3.1-8B-EZO-1.1-it-GGUF", - "downloads": 460, + "description": "ELYZA-japanese-CodeLlama-7b-instruct-gguf ELYZAさんが公開しているELYZA-japanese-CodeLlama-7b-instructのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/ELYZA-japanese-CodeLlama-7b-instruct-gguf", + "project_name": "ELYZA-japanese-CodeLlama-7b-instruct-gguf", + "downloads": 448, "source": "Hugging Face", - "score": -0.1072186733958599, - "first_commit": "2024-07-31 12:12:01", - "latest_commit": "2024-07-31 18:13:59", + "score": -0.08804398473598075, + "first_commit": "2023-11-15 09:48:32", + "latest_commit": "2023-11-16 14:28:24", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, + "model_size": 6.74, "model_architectures": null }, { - "description": "Swallow Our Swallow model has undergone continual pre-training from the Llama 2 family, primarily with the addition of Japanese language data.", - "url": "https://huggingface.co/tokyotech-llm/Swallow-13b-NVE-hf", - "project_name": "Swallow-13b-NVE-hf", - "downloads": 459, + "description": "bert-base-japanese-wikipedia-ud-head Model Description", + "url": "https://huggingface.co/KoichiYasuoka/bert-base-japanese-wikipedia-ud-head", + "project_name": "bert-base-japanese-wikipedia-ud-head", + "downloads": 447, "source": "Hugging Face", - "score": -0.1072343847525541, - "first_commit": "2024-01-30 11:39:05", - "latest_commit": "2024-06-29 08:56:22", + "score": -0.08805458968651708, + "first_commit": "2022-06-20 21:58:53", + "latest_commit": "2023-03-04 20:16:55", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "LlamaForCausalLM" + "model_architectures": "BertForQuestionAnswering" }, { - "description": "JaCWIR: Japanese Casual Web IR - 日本語情報検索評価のための小規模でカジュアルなWebタイトルと概要のデータセット 近年、大規模言語モデル（LLM）の台頭により、一��的な日本語を用いた自然な検索クエリで質問するユースケースが増えています。", - "url": "https://huggingface.co/datasets/hotchpotch/JaCWIR", - "project_name": "JaCWIR", - "downloads": 458, + "description": "読み込み方 from datasets import load_dataset dataset = load_dataset(\"YANS-official/senryu-test\", split=\"test\") 概要 川柳投稿サイトの『写真川柳』と『川柳投稿まるせん』のクロールデータ、および YANS 委員が作成したデータを含みます。 ", + "url": "https://huggingface.co/datasets/YANS-official/senryu-test", + "project_name": "senryu-test", + "downloads": 440, "source": "Hugging Face", - "score": -0.10725009610924832, - "first_commit": "2024-03-23 05:57:58", - "latest_commit": "2024-04-01 02:34:34", + "score": -0.08812882434027142, + "first_commit": "2024-09-03 15:02:47", + "latest_commit": "2024-09-09 05:53:26", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "This repository is publicly accessible, but you have to accept the conditions to access its files and content.", - "url": "https://huggingface.co/stabilityai/japanese-stablelm-instruct-alpha-7b", - "project_name": "japanese-stablelm-instruct-alpha-7b", - "downloads": 455, + "description": "umiyuki-Japanese-Chat-Umievo-itr001-7b-gguf umiyukiさんが公開しているJapanese-Chat-Umievo-itr001-7bのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/umiyuki-Japanese-Chat-Umievo-itr001-7b-gguf", + "project_name": "umiyuki-Japanese-Chat-Umievo-itr001-7b-gguf", + "downloads": 426, "source": "Hugging Face", - "score": -0.10729723017933097, - "first_commit": null, - "latest_commit": null, + "score": -0.08827729364778009, + "first_commit": "2024-04-27 09:55:39", + "latest_commit": "2024-04-27 10:52:17", "languages": [], "model_or_dataset": "model", - "model_size": null, + "model_size": 7.24, "model_architectures": null }, { - "description": "This repository contains some GGUF quantizations of the merge of the VNTL LLaMA 3 8B qlora.", - "url": "https://huggingface.co/lmg-anon/vntl-llama3-8b-gguf", - "project_name": "vntl-llama3-8b-gguf", - "downloads": 443, + "description": "ELYZA-japanese-Llama-2-13b-fast-gguf ELYZAさんが公開しているELYZA-japanese-Llama-2-13b-fastのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-13b-fast-gguf", + "project_name": "ELYZA-japanese-Llama-2-13b-fast-gguf", + "downloads": 424, "source": "Hugging Face", - "score": -0.10748576645966158, - "first_commit": "2024-06-13 17:17:30", - "latest_commit": "2024-06-15 17:33:02", + "score": -0.08829850354885276, + "first_commit": "2023-12-27 10:40:52", + "latest_commit": "2023-12-27 13:18:46", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, + "model_size": 13.1, "model_architectures": null }, { - "description": "Chat & support: TheBloke's Discord server Want to contribute?", - "url": "https://huggingface.co/TheBloke/japanese-stablelm-instruct-gamma-7B-GGUF", - "project_name": "japanese-stablelm-instruct-gamma-7B-GGUF", - "downloads": 442, + "description": "JQaRA : Japanese Question Answering with Retrieval Augmentation - 検索拡張(RAG)評価のための日本語 Q&A データセット 高性能な LLM の台頭に伴い、LLM を用いた質疑応答のユースケースが増加しています。", + "url": "https://huggingface.co/datasets/hotchpotch/JQaRA", + "project_name": "JQaRA", + "downloads": 421, "source": "Hugging Face", - "score": -0.1075014778163558, - "first_commit": "2023-10-28 19:03:17", - "latest_commit": "2023-10-28 19:07:41", + "score": -0.08833031840046177, + "first_commit": "2024-03-03 01:58:34", + "latest_commit": "2024-08-10 02:56:05", "languages": [], - "model_or_dataset": "model", - "model_size": 7.24, + "model_or_dataset": "dataset", + "model_size": null, "model_architectures": null }, { - "description": "Tanuki-8x8B-dpo-v1.0-AWQ 概要 GENIAC 松尾研 LLM開発プロジェクトで開発されたLLMであるweblab-GENIAC/Tanuki-8x8B-dpo-v1.0のAWQ 4bit量子化モデルです。", - "url": "https://huggingface.co/team-hatakeyama-phase2/Tanuki-8x8B-dpo-v1.0-AWQ", - "project_name": "Tanuki-8x8B-dpo-v1.0-AWQ", - "downloads": 436, + "description": "Japanese Natural Language Inference Model", + "url": "https://huggingface.co/cyberagent/xlm-roberta-large-jnli-jsick", + "project_name": "xlm-roberta-large-jnli-jsick", + "downloads": 418, "source": "Hugging Face", - "score": -0.1075957459565211, - "first_commit": "2024-08-27 09:31:22", - "latest_commit": "2024-09-03 09:26:20", + "score": -0.08836213325207076, + "first_commit": "2022-12-23 10:51:12", + "latest_commit": "2022-12-23 10:51:12", "languages": [], "model_or_dataset": "model", - "model_size": 6.75, - "model_architectures": "TanukiForCausalLM" + "model_size": null, + "model_architectures": "XLMRobertaForSequenceClassification" }, { "description": "rinna/japanese-hubert-large Overview This is a Japanese HuBERT Large model trained by rinna Co.", "url": "https://huggingface.co/rinna/japanese-hubert-large", "project_name": "japanese-hubert-large", - "downloads": 433, + "downloads": 414, "source": "Hugging Face", - "score": -0.10764288002660376, + "score": -0.0884045530542161, "first_commit": "2024-03-05 10:24:37", "latest_commit": "2024-07-22 08:12:21", "languages": [], @@ -6023,56 +6057,84 @@ "model_architectures": "HubertModel" }, { - "description": "hubert-base-jtube This repo provides model weights for the hubert-base model trained on the JTubeSpeech corpus. ", - "url": "https://huggingface.co/sarulab-speech/hubert-base-jtube", - "project_name": "hubert-base-jtube", - "downloads": 431, + "description": "This is a Japanese sentence-LUKE model.", + "url": "https://huggingface.co/cheonboy/sentence_embedding_japanese", + "project_name": "sentence_embedding_japanese", + "downloads": 413, "source": "Hugging Face", - "score": -0.10767430273999219, - "first_commit": "2024-02-02 04:15:22", - "latest_commit": "2024-02-05 11:49:57", + "score": -0.08841515800475243, + "first_commit": "2023-10-05 05:10:25", + "latest_commit": "2023-10-05 05:13:09", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "HubertModel" + "model_architectures": "LukeModel" }, { - "description": "bert-base-japanese-wikipedia-ud-head Model Description", - "url": "https://huggingface.co/KoichiYasuoka/bert-base-japanese-wikipedia-ud-head", - "project_name": "bert-base-japanese-wikipedia-ud-head", - "downloads": 431, + "description": "License:CreativeML Open RAIL-M Additional Copyright: sazyou_roukaku (TwitterID @sazyou_roukaku) as of June 25, 2023 このモデルは『CreativeML Open RAIL-M』でLicenseそのものに変更はありません。 ", + "url": "https://huggingface.co/sazyou-roukaku/LittleStepMix", + "project_name": "LittleStepMix", + "downloads": 411, "source": "Hugging Face", - "score": -0.10767430273999219, - "first_commit": "2022-06-20 21:58:53", - "latest_commit": "2023-03-04 20:16:55", + "score": -0.0884363679058251, + "first_commit": "2023-06-25 06:57:42", + "latest_commit": "2023-07-04 10:47:46", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "BertForQuestionAnswering" + "model_architectures": null }, { - "description": "(简体中文|English|日本語) Introduction github repo : https://github.com/FunAudioLLM/SenseVoice SenseVoice is a speech foundation model with multiple speech understanding capabilities, including automatic speech recognition (ASR), spoken language identification (LID), speech emotion recognition (SER), and audio event detection (AED).", - "url": "https://huggingface.co/FunAudioLLM/SenseVoiceSmall", - "project_name": "SenseVoiceSmall", - "downloads": 428, + "description": "hubert-base-jtube This repo provides model weights for the hubert-base model trained on the JTubeSpeech corpus. ", + "url": "https://huggingface.co/sarulab-speech/hubert-base-jtube", + "project_name": "hubert-base-jtube", + "downloads": 410, "source": "Hugging Face", - "score": -0.10772143681007484, - "first_commit": "2024-07-03 03:56:49", - "latest_commit": "2024-07-31 05:47:48", + "score": -0.08844697285636144, + "first_commit": "2024-02-02 04:15:22", + "latest_commit": "2024-02-05 11:49:57", "languages": [], "model_or_dataset": "model", "model_size": null, + "model_architectures": "HubertModel" + }, + { + "description": "This is a Japanese translated version of HumanEval, an evaluation harness for the HumanEval problem solving dataset described in the paper \"Evaluating Large Language Models Trained on Code\".", + "url": "https://huggingface.co/datasets/kogi-jwu/jhumaneval", + "project_name": "jhumaneval", + "downloads": 410, + "source": "Hugging Face", + "score": -0.08844697285636144, + "first_commit": "2023-10-21 08:20:14", + "latest_commit": "2024-01-10 21:52:35", + "languages": [], + "model_or_dataset": "dataset", + "model_size": null, "model_architectures": null }, { - "description": "JQaRA : Japanese Question Answering with Retrieval Augmentation - 検索拡張(RAG)評価のための日本語 Q&A データセット 高性能な LLM の台頭に伴い、LLM を用いた質疑応答のユースケースが増加しています。", - "url": "https://huggingface.co/datasets/hotchpotch/JQaRA", - "project_name": "JQaRA", - "downloads": 425, + "description": "tokyotech-llm-Swallow-13b-instruct-v0.1-gguf tokyotech-llmさんが公開しているSwallow-13b-instruct-v0.1のggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/tokyotech-llm-Swallow-13b-instruct-v0.1-gguf", + "project_name": "tokyotech-llm-Swallow-13b-instruct-v0.1-gguf", + "downloads": 409, "source": "Hugging Face", - "score": -0.1077685708801575, - "first_commit": "2024-03-03 01:58:34", - "latest_commit": "2024-08-10 02:56:05", + "score": -0.08845757780689777, + "first_commit": "2024-05-02 14:18:27", + "latest_commit": "2024-05-03 04:36:24", + "languages": [], + "model_or_dataset": "model", + "model_size": 13.1, + "model_architectures": null + }, + { + "description": "JaCWIR: Japanese Casual Web IR - 日本語情報検索評価のための小規模でカジュアルなWebタイトルと概要のデータセット 近年、大規模言語モデル（LLM）の台頭により、一般的な日本語を用いた自然な検索クエリで質問するユースケースが増えています。", + "url": "https://huggingface.co/datasets/hotchpotch/JaCWIR", + "project_name": "JaCWIR", + "downloads": 407, + "source": "Hugging Face", + "score": -0.08847878770797044, + "first_commit": "2024-03-23 05:57:58", + "latest_commit": "2024-04-01 02:34:34", "languages": [], "model_or_dataset": "dataset", "model_size": null, @@ -6080,95 +6142,109 @@ }, { "description": "Chat & support: TheBloke's Discord server Want to contribute?", - "url": "https://huggingface.co/TheBloke/japanese-stablelm-instruct-beta-7B-GGUF", - "project_name": "japanese-stablelm-instruct-beta-7B-GGUF", - "downloads": 418, + "url": "https://huggingface.co/TheBloke/japanese-stablelm-instruct-gamma-7B-GGUF", + "project_name": "japanese-stablelm-instruct-gamma-7B-GGUF", + "downloads": 406, "source": "Hugging Face", - "score": -0.10787855037701702, - "first_commit": "2023-11-03 01:04:31", - "latest_commit": "2023-11-03 12:54:55", + "score": -0.08848939265850678, + "first_commit": "2023-10-28 19:03:17", + "latest_commit": "2023-10-28 19:07:41", "languages": [], "model_or_dataset": "model", - "model_size": 6.74, + "model_size": 7.24, "model_architectures": null }, { - "description": "Tanuki-8x8B-dpo-v1.0 モデルについて Tanuki-8x8Bは、フルスクラッチで約1.7Tトークン事前学習を行った8x8Bパラメータ（総パラメータ約47B、アクティブパラメータ約13B）の大規模言語モデルです。", - "url": "https://huggingface.co/weblab-GENIAC/Tanuki-8x8B-dpo-v1.0", - "project_name": "Tanuki-8x8B-dpo-v1.0", - "downloads": 417, + "description": "bert-base-japanese-v3-unsup-simcse-jawiki 「大規模言語モデル入門」の第8章で紹介している教師なしSimCSEのモデルです。 ", + "url": "https://huggingface.co/llm-book/bert-base-japanese-v3-unsup-simcse-jawiki", + "project_name": "bert-base-japanese-v3-unsup-simcse-jawiki", + "downloads": 405, "source": "Hugging Face", - "score": -0.10789426173371124, - "first_commit": "2024-08-12 12:47:11", - "latest_commit": "2024-09-02 23:47:09", + "score": -0.0884999976090431, + "first_commit": "2023-06-21 10:52:27", + "latest_commit": "2023-07-24 07:07:44", "languages": [], "model_or_dataset": "model", - "model_size": 47.0, - "model_architectures": "TanukiForCausalLM" + "model_size": null, + "model_architectures": "BertModel" }, { - "description": "gemma-2-2b-it-gguf googleさんが公開しているgemma-2-2b-itのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/gemma-2-2b-it-gguf", - "project_name": "gemma-2-2b-it-gguf", - "downloads": 412, + "description": "Model Card for Japanese BART large Model description", + "url": "https://huggingface.co/ku-nlp/bart-large-japanese", + "project_name": "bart-large-japanese", + "downloads": 400, "source": "Hugging Face", - "score": -0.10797281851718231, - "first_commit": "2024-08-01 17:22:58", - "latest_commit": "2024-08-01 18:29:08", + "score": -0.08855302236172477, + "first_commit": "2023-05-09 07:44:59", + "latest_commit": "2023-05-12 11:05:03", "languages": [], "model_or_dataset": "model", - "model_size": 2.61, - "model_architectures": null + "model_size": null, + "model_architectures": "MBartForConditionalGeneration" }, { - "description": "umiyuki-Umievo-itr012-Gleipnir-7B-gguf umiyukiさんが公開しているUmievo-itr012-Gleipnir-7Bのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/umiyuki-Umievo-itr012-Gleipnir-7B-gguf", - "project_name": "umiyuki-Umievo-itr012-Gleipnir-7B-gguf", - "downloads": 411, + "description": "Phi-3-medium-128k-instruct-gguf microsoftさんが公開しているPhi-3-medium-128k-instructのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Phi-3-medium-128k-instruct-gguf", + "project_name": "Phi-3-medium-128k-instruct-gguf", + "downloads": 399, "source": "Hugging Face", - "score": -0.10798852987387653, - "first_commit": "2024-05-29 15:05:32", - "latest_commit": "2024-05-29 15:53:40", + "score": -0.08856362731226111, + "first_commit": "2024-05-22 15:27:33", + "latest_commit": "2024-05-22 16:56:55", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, + "model_size": 14.0, "model_architectures": null }, { - "description": "whisper-large-v2-japanese-5k-steps This model is a fine-tuned version of openai/whisper-large-v2 on the Japanese CommonVoice dataset (v11)..", - "url": "https://huggingface.co/clu-ling/whisper-large-v2-japanese-5k-steps", - "project_name": "whisper-large-v2-japanese-5k-steps", - "downloads": 411, + "description": "読み込み方 from datasets import load_dataset dataset = load_dataset(\"YANS-official/senryu-marusen\", split=\"train\") 概要 月に1万句以上の投稿がある国内最大級の川柳投稿サイト『川柳投稿まるせん』のクロールデータです。", + "url": "https://huggingface.co/datasets/YANS-official/senryu-marusen", + "project_name": "senryu-marusen", + "downloads": 398, "source": "Hugging Face", - "score": -0.10798852987387653, - "first_commit": "2023-01-28 22:14:29", - "latest_commit": "2023-03-03 21:11:39", + "score": -0.08857423226279744, + "first_commit": "2024-08-28 18:49:03", + "latest_commit": "2024-08-30 11:41:46", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "WhisperForConditionalGeneration" + "model_architectures": null }, { - "description": "回答と回答が出てくるパラグラフを与えると質問文を生成するモデル SEE: https://github.com/sonoisa/deep-question-generation 本モデルの作成ステップ概要 SQuAD 1.1を日本語に機械翻訳し、不正なデータをクレンジング（有効なデータは約半分）。", - "url": "https://huggingface.co/sonoisa/t5-base-japanese-question-generation", - "project_name": "t5-base-japanese-question-generation", - "downloads": 404, + "description": "recruit-jp/japanese-typo-detector-roberta-base モデルの概要 日本語の文章を入力すると各文字ごとに誤字脱字である確率を出力します 各ラベルの意味は以下の通りです id label meaning 0 OK 誤字なし 1 deletion 1文字の抜け 2 insertion_a 余分な1文字の挿入 3 insertion_b 直前の文字列と一致する２文字以上の余分な文字の挿入 4 kanji-conversion_a 同一の読みを持つ漢字の入れ替え（誤変換） 5 kanji-conversion_b 近い読みを持つ漢字の入れ替え（誤変換） 6 substitution 1文字の入れ替え 7 transposition 隣接する２文字間の転置 8 others その他の入力誤り 誤り種類の詳細については学習データセットの元論文をご参照ください 日本語 Wikipedia の編集履歴に基づく 入力誤りデータセットと訂正システムの改良 その他、モデルの詳細については当社ブログ記事をご参照ください 誤字脱字検出モデルをHugging Face Hubに公開しました (Re", + "url": "https://huggingface.co/recruit-jp/japanese-typo-detector-roberta-base", + "project_name": "japanese-typo-detector-roberta-base", + "downloads": 397, "source": "Hugging Face", - "score": -0.10809850937073605, - "first_commit": "2021-04-03 14:08:55", - "latest_commit": "2022-03-11 02:50:33", + "score": -0.08858483721333378, + "first_commit": "2023-11-09 06:27:40", + "latest_commit": "2023-12-21 03:07:31", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "T5ForConditionalGeneration" + "model_size": 0.0996, + "model_architectures": "RobertaForTokenClassification" + }, + { + "description": "Chat & support: TheBloke's Discord server Want to contribute?", + "url": "https://huggingface.co/TheBloke/japanese-stablelm-instruct-beta-7B-GGUF", + "project_name": "japanese-stablelm-instruct-beta-7B-GGUF", + "downloads": 397, + "source": "Hugging Face", + "score": -0.08858483721333378, + "first_commit": "2023-11-03 01:04:31", + "latest_commit": "2023-11-03 12:54:55", + "languages": [], + "model_or_dataset": "model", + "model_size": 6.74, + "model_architectures": null }, { "description": "Japanese Laws This dataset comprises 8.75K law records retrieved from the official Japanese government website e-Gov. ", "url": "https://huggingface.co/datasets/y2lan/japan-law", "project_name": "japan-law", - "downloads": 393, + "downloads": 397, "source": "Hugging Face", - "score": -0.10827133429437244, + "score": -0.08858483721333378, "first_commit": "2023-07-20 06:26:25", "latest_commit": "2023-07-20 06:45:14", "languages": [], @@ -6177,56 +6253,84 @@ "model_architectures": null }, { - "description": "hh-rlhf-12k-ja This repository provides a human preference dataset developed by LLM-jp, a collaborative project launched in Japan.", - "url": "https://huggingface.co/datasets/llm-jp/hh-rlhf-12k-ja", - "project_name": "hh-rlhf-12k-ja", - "downloads": 393, + "description": "Llama3-ArrowSE-8B-v0.3-gguf DataPilotさんが公開しているLlama3-ArrowSE-8B-v0.3のggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Llama3-ArrowSE-8B-v0.3-gguf", + "project_name": "Llama3-ArrowSE-8B-v0.3-gguf", + "downloads": 384, "source": "Hugging Face", - "score": -0.10827133429437244, - "first_commit": "2024-02-04 21:19:53", - "latest_commit": "2024-02-04 21:45:59", + "score": -0.08872270157030611, + "first_commit": "2024-07-07 07:27:12", + "latest_commit": "2024-07-07 09:30:16", + "languages": [], + "model_or_dataset": "model", + "model_size": 8.03, + "model_architectures": null + }, + { + "description": "Githubリポジトリstockmarkteam/ner-wikipedia-datasetで公開されているデータセットを利用しています。", + "url": "https://huggingface.co/datasets/llm-book/ner-wikipedia-dataset", + "project_name": "ner-wikipedia-dataset", + "downloads": 381, + "source": "Hugging Face", + "score": -0.08875451642191512, + "first_commit": "2023-04-15 10:43:21", + "latest_commit": "2023-12-12 11:25:51", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "lightblue-suzume-llama-3-8B-multilingual-gguf lightblueさんが公開しているsuzume-llama-3-8B-multilingualのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/lightblue-suzume-llama-3-8B-multilingual-gguf", - "project_name": "lightblue-suzume-llama-3-8B-multilingual-gguf", - "downloads": 391, + "description": "日本語T5 Prefix Language Model", + "url": "https://huggingface.co/sonoisa/t5-base-japanese-adapt", + "project_name": "t5-base-japanese-adapt", + "downloads": 380, "source": "Hugging Face", - "score": -0.10830275700776087, - "first_commit": "2024-05-06 16:31:55", - "latest_commit": "2024-05-07 12:59:57", + "score": -0.08876512137245145, + "first_commit": "2022-08-27 08:51:11", + "latest_commit": "2022-11-05 09:34:10", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": null + "model_size": null, + "model_architectures": "T5ForConditionalGeneration" }, { - "description": "Meta-Llama-3-8B-Instruct-gguf meta-llamaさんが公開しているMeta-Llama-3-8B-Instructのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Meta-Llama-3-8B-Instruct-gguf", - "project_name": "Meta-Llama-3-8B-Instruct-gguf", - "downloads": 389, + "description": "luke-japanese luke-japanese is the Japanese version of LUKE (Language Understanding with Knowledge-based Embeddings), a pre-trained knowledge-enhanced contextualized representation of words and entities.", + "url": "https://huggingface.co/studio-ousia/luke-japanese-base-lite", + "project_name": "luke-japanese-base-lite", + "downloads": 379, "source": "Hugging Face", - "score": -0.10833417972114931, - "first_commit": "2024-05-12 07:18:00", - "latest_commit": "2024-05-12 08:08:38", + "score": -0.08877572632298779, + "first_commit": "2022-10-25 09:27:16", + "latest_commit": "2022-11-09 15:22:22", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": null + "model_size": null, + "model_architectures": "LukeForMaskedLM" }, { - "description": "Llama3-ArrowSE-8B-v0.3-gguf DataPilotさんが公開しているLlama3-ArrowSE-8B-v0.3のggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Llama3-ArrowSE-8B-v0.3-gguf", - "project_name": "Llama3-ArrowSE-8B-v0.3-gguf", - "downloads": 389, + "description": "whisper-large-v2-japanese-5k-steps This model is a fine-tuned version of openai/whisper-large-v2 on the Japanese CommonVoice dataset (v11)..", + "url": "https://huggingface.co/clu-ling/whisper-large-v2-japanese-5k-steps", + "project_name": "whisper-large-v2-japanese-5k-steps", + "downloads": 371, "source": "Hugging Face", - "score": -0.10833417972114931, - "first_commit": "2024-07-07 07:27:12", - "latest_commit": "2024-07-07 09:30:16", + "score": -0.08886056592727845, + "first_commit": "2023-01-28 22:14:29", + "latest_commit": "2023-03-03 21:11:39", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "WhisperForConditionalGeneration" + }, + { + "description": "lightblue-suzume-llama-3-8B-multilingual-gguf lightblueさんが公開しているsuzume-llama-3-8B-multilingualのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/lightblue-suzume-llama-3-8B-multilingual-gguf", + "project_name": "lightblue-suzume-llama-3-8B-multilingual-gguf", + "downloads": 370, + "source": "Hugging Face", + "score": -0.08887117087781479, + "first_commit": "2024-05-06 16:31:55", + "latest_commit": "2024-05-07 12:59:57", "languages": [], "model_or_dataset": "model", "model_size": 8.03, @@ -6236,9 +6340,9 @@ "description": "aya-23-35B-gguf CohereForAIさんが公開しているaya-23-35Bのggufフォーマット変換版です。 ", "url": "https://huggingface.co/mmnga/aya-23-35B-gguf", "project_name": "aya-23-35B-gguf", - "downloads": 388, + "downloads": 366, "source": "Hugging Face", - "score": -0.10834989107784353, + "score": -0.08891359067996013, "first_commit": "2024-05-26 16:32:27", "latest_commit": "2024-05-27 00:47:56", "languages": [], @@ -6247,40 +6351,26 @@ "model_architectures": null }, { - "description": "Phi-3-medium-128k-instruct-gguf microsoftさんが公開しているPhi-3-medium-128k-instructのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Phi-3-medium-128k-instruct-gguf", - "project_name": "Phi-3-medium-128k-instruct-gguf", - "downloads": 387, - "source": "Hugging Face", - "score": -0.10836560243453774, - "first_commit": "2024-05-22 15:27:33", - "latest_commit": "2024-05-22 16:56:55", - "languages": [], - "model_or_dataset": "model", - "model_size": 14.0, - "model_architectures": null - }, - { - "description": "BERT large Japanese (character-level tokenization with whole word masking, CC-100 and jawiki-20230102)", - "url": "https://huggingface.co/tohoku-nlp/bert-large-japanese-char-v2", - "project_name": "bert-large-japanese-char-v2", - "downloads": 386, + "description": "ElanMT ElanMT-BT-en-ja is a English to Japanese translation model developed by ELAN MITSUA Project / Abstract Engine.", + "url": "https://huggingface.co/Mitsua/elan-mt-bt-en-ja", + "project_name": "elan-mt-bt-en-ja", + "downloads": 361, "source": "Hugging Face", - "score": -0.10838131379123196, - "first_commit": "2023-05-19 00:48:06", - "latest_commit": "2023-05-19 00:54:57", + "score": -0.0889666154326418, + "first_commit": "2024-05-20 01:51:18", + "latest_commit": "2024-05-20 01:53:38", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForPreTraining" + "model_size": 0.0606, + "model_architectures": "MarianMTModel" }, { "description": "Model card for model ID", "url": "https://huggingface.co/retrieva-jp/t5-base-long", "project_name": "t5-base-long", - "downloads": 380, + "downloads": 355, "source": "Hugging Face", - "score": -0.10847558193139727, + "score": -0.0890302451358598, "first_commit": "2023-04-26 08:30:59", "latest_commit": "2023-05-10 10:00:00", "languages": [], @@ -6289,69 +6379,138 @@ "model_architectures": "T5ForConditionalGeneration" }, { - "description": "ku-nlp/roberta-base-japanese-char-wwm Model description This is a Japanese RoBERTa base model pre-trained on Japanese Wikipedia and the Japanese portion of CC-100.", - "url": "https://huggingface.co/ku-nlp/roberta-base-japanese-char-wwm", - "project_name": "roberta-base-japanese-char-wwm", - "downloads": 379, + "description": "c4ai-command-r-plus-gguf CohereForAIさんが公開しているc4ai-command-r-plusのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/c4ai-command-r-plus-gguf", + "project_name": "c4ai-command-r-plus-gguf", + "downloads": 351, "source": "Hugging Face", - "score": -0.10849129328809148, - "first_commit": "2022-09-20 05:07:34", - "latest_commit": "2023-03-20 08:05:45", + "score": -0.08907266493800513, + "first_commit": "2024-04-22 14:46:41", + "latest_commit": "2024-04-23 16:13:37", "languages": [], "model_or_dataset": "model", - "model_size": 0.1, - "model_architectures": "RobertaForMaskedLM" + "model_size": null, + "model_architectures": null }, { - "description": "License:CreativeML Open RAIL-M Additional Copyright: sazyou_roukaku (TwitterID @sazyou_roukaku) as of June 25, 2023 このモデルは『CreativeML Open RAIL-M』でLicenseそのものに変更はありません。 ", - "url": "https://huggingface.co/sazyou-roukaku/LittleStepMix", - "project_name": "LittleStepMix", - "downloads": 378, + "description": "Model Card for Japanese DeBERTa V2 tiny Model description", + "url": "https://huggingface.co/ku-nlp/deberta-v2-tiny-japanese", + "project_name": "deberta-v2-tiny-japanese", + "downloads": 350, "source": "Hugging Face", - "score": -0.1085070046447857, - "first_commit": "2023-06-25 06:57:42", - "latest_commit": "2023-07-04 10:47:46", + "score": -0.08908326988854147, + "first_commit": "2023-01-18 13:36:09", + "latest_commit": "2023-03-23 16:13:46", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.013900000000000001, + "model_architectures": "DebertaV2ForMaskedLM" + }, + { + "description": "Meta-Llama-3-8B-Instruct-gguf meta-llamaさんが公開しているMeta-Llama-3-8B-Instructのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Meta-Llama-3-8B-Instruct-gguf", + "project_name": "Meta-Llama-3-8B-Instruct-gguf", + "downloads": 349, + "source": "Hugging Face", + "score": -0.0890938748390778, + "first_commit": "2024-05-12 07:18:00", + "latest_commit": "2024-05-12 08:08:38", "languages": [], "model_or_dataset": "model", + "model_size": 8.03, + "model_architectures": null + }, + { + "description": "Dataset Details Dataset Type:Japanese LLaVA Instruct 150K is a localized version of the original LLaVA Visual Instruct 150K dataset.", + "url": "https://huggingface.co/datasets/turing-motors/LLaVA-Instruct-150K-JA", + "project_name": "LLaVA-Instruct-150K-JA", + "downloads": 348, + "source": "Hugging Face", + "score": -0.08910447978961414, + "first_commit": null, + "latest_commit": null, + "languages": [], + "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "Japanese Dictionary", - "url": "https://github.com/gojp/nihongo", - "project_name": "nihongo", - "stargazers_count": 78, + "description": "OcuteusのGGUF版です。 ", + "url": "https://huggingface.co/Local-Novel-LLM-project/Ocuteus-v1-gguf", + "project_name": "Ocuteus-v1-gguf", + "downloads": 347, + "source": "Hugging Face", + "score": -0.08911508474015047, + "first_commit": "2024-05-07 09:57:49", + "latest_commit": "2024-05-10 06:18:35", + "languages": [], + "model_or_dataset": "model", + "model_size": 7.24, + "model_architectures": null + }, + { + "description": "YuisekinAIEvol-Mistral-7B-ja-math-v0.1.1-gguf yuisekiさんが公開しているYuisekinAIEvol-Mistral-7B-ja-math-v0.1.1のggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/YuisekinAIEvol-Mistral-7B-ja-math-v0.1.1-gguf", + "project_name": "YuisekinAIEvol-Mistral-7B-ja-math-v0.1.1-gguf", + "downloads": 346, + "source": "Hugging Face", + "score": -0.08912568969068681, + "first_commit": "2024-04-29 14:18:07", + "latest_commit": "2024-04-29 15:52:08", + "languages": [], + "model_or_dataset": "model", + "model_size": 7.24, + "model_architectures": null + }, + { + "description": "このツールは、複数のデータセットを横断して日本語の大規模言語モデルを自動評価するものです．", + "url": "https://github.com/llm-jp/llm-jp-eval", + "project_name": "llm-jp-eval", + "stargazers_count": 84, "source": "GitHub", - "score": -0.10867781892454018, - "first_commit": "2013-09-03 00:22:50", - "latest_commit": "2024-02-07 18:36:24", + "score": -0.08915516896837347, + "first_commit": "2023-10-19 19:36:10", + "latest_commit": "2024-07-18 21:31:53", "languages": [ - "Go", "Python" ], "model_or_dataset": null }, { - "description": "A large parallel corpus of English and Japanese", - "url": "https://github.com/rpryzant/JESC", - "project_name": "JESC", - "stargazers_count": 78, - "source": "GitHub", - "score": -0.10867781892454018, - "first_commit": "2017-10-25 07:41:35", - "latest_commit": "2017-10-31 21:08:56", - "languages": [ - "Python" - ], - "model_or_dataset": "dataset" + "description": "日本語版CLIPモデル This is a CLIP text/image encoder model for Japanese. ", + "url": "https://huggingface.co/sonoisa/clip-vit-b-32-japanese-v1", + "project_name": "clip-vit-b-32-japanese-v1", + "downloads": 340, + "source": "Hugging Face", + "score": -0.0891893193939048, + "first_commit": "2022-02-15 15:47:34", + "latest_commit": "2022-04-19 14:18:58", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "BertModel" + }, + { + "description": "Model card for model ID", + "url": "https://huggingface.co/retrieva-jp/t5-large-short", + "project_name": "t5-large-short", + "downloads": 336, + "source": "Hugging Face", + "score": -0.08923173919605014, + "first_commit": "2023-04-26 08:18:58", + "latest_commit": "2023-05-10 10:00:54", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "T5ForConditionalGeneration" }, { "description": "llm-book/t5-base-long-livedoor-news-corpus 「大規模言語モデル入門」の第7章で紹介している要約生成のモデルです。 ", "url": "https://huggingface.co/llm-book/t5-base-long-livedoor-news-corpus", "project_name": "t5-base-long-livedoor-news-corpus", - "downloads": 363, + "downloads": 335, "source": "Hugging Face", - "score": -0.10874267499519895, + "score": -0.08924234414658648, "first_commit": "2023-06-27 13:32:54", "latest_commit": "2023-07-25 13:10:36", "languages": [], @@ -6360,96 +6519,96 @@ "model_architectures": "T5ForConditionalGeneration" }, { - "description": "This is a model for named entity recognition of Japanese medical documents.", - "url": "https://huggingface.co/sociocom/MedNER-CR-JA", - "project_name": "MedNER-CR-JA", - "downloads": 356, + "description": "Orion-14B 🌐English | 🇨", + "url": "https://huggingface.co/OrionStarAI/Orion-14B-Chat", + "project_name": "Orion-14B-Chat", + "downloads": 333, "source": "Hugging Face", - "score": -0.10885265449205847, - "first_commit": "2022-08-23 03:30:43", - "latest_commit": "2024-07-31 07:44:00", + "score": -0.08926355404765914, + "first_commit": "2024-01-16 06:03:30", + "latest_commit": "2024-04-11 10:48:51", "languages": [], "model_or_dataset": "model", - "model_size": 0.11, - "model_architectures": "BertForTokenClassification" + "model_size": 14.5, + "model_architectures": "OrionForCausalLM" }, { - "description": "ElanMT ElanMT-BT-en-ja is a English to Japanese translation model developed by ELAN MITSUA Project / Abstract Engine.", - "url": "https://huggingface.co/Mitsua/elan-mt-bt-en-ja", - "project_name": "elan-mt-bt-en-ja", - "downloads": 356, + "description": "記事本文からタイトルを生成するモデル SEE: https://qiita.com/sonoisa/items/a9af64ff641f0bbfed44", + "url": "https://huggingface.co/sonoisa/t5-base-japanese-title-generation", + "project_name": "t5-base-japanese-title-generation", + "downloads": 331, "source": "Hugging Face", - "score": -0.10885265449205847, - "first_commit": "2024-05-20 01:51:18", - "latest_commit": "2024-05-20 01:53:38", + "score": -0.0892847639487318, + "first_commit": "2021-04-04 06:57:18", + "latest_commit": "2022-02-21 13:38:09", "languages": [], "model_or_dataset": "model", - "model_size": 0.0606, - "model_architectures": "MarianMTModel" + "model_size": null, + "model_architectures": "T5ForConditionalGeneration" }, { - "description": "umiyuki-Japanese-Chat-Umievo-itr001-7b-gguf umiyukiさんが公開しているJapanese-Chat-Umievo-itr001-7bのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/umiyuki-Japanese-Chat-Umievo-itr001-7b-gguf", - "project_name": "umiyuki-Japanese-Chat-Umievo-itr001-7b-gguf", - "downloads": 356, + "description": "What’s this?", + "url": "https://huggingface.co/globis-university/deberta-v3-japanese-large", + "project_name": "deberta-v3-japanese-large", + "downloads": 330, "source": "Hugging Face", - "score": -0.10885265449205847, - "first_commit": "2024-04-27 09:55:39", - "latest_commit": "2024-04-27 10:52:17", + "score": -0.08929536889926815, + "first_commit": "2023-09-21 16:15:15", + "latest_commit": "2024-07-05 05:50:06", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": null + "model_size": null, + "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "日本語版CLIPモデル This is a CLIP text/image encoder model for Japanese. ", - "url": "https://huggingface.co/sonoisa/clip-vit-b-32-japanese-v1", - "project_name": "clip-vit-b-32-japanese-v1", - "downloads": 351, + "description": "old？ ", + "url": "https://huggingface.co/Lasorco/lametta_old", + "project_name": "lametta_old", + "downloads": 330, "source": "Hugging Face", - "score": -0.10893121127552956, - "first_commit": "2022-02-15 15:47:34", - "latest_commit": "2022-04-19 14:18:58", + "score": -0.08929536889926815, + "first_commit": "2023-05-21 11:16:50", + "latest_commit": "2024-07-23 07:24:33", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "BertModel" + "model_architectures": null }, { - "description": "Japanese CLIP ViT-H/14 (Wider) Table of Contents Overview Usage Model Details Evaluation Limitations and Biases Citation See Also Contact Information Overview Developed by:", - "url": "https://huggingface.co/hakuhodo-tech/japanese-clip-vit-h-14-bert-wider", - "project_name": "japanese-clip-vit-h-14-bert-wider", - "downloads": 350, + "description": "hh-rlhf-12k-ja This repository provides a human preference dataset developed by LLM-jp, a collaborative project launched in Japan.", + "url": "https://huggingface.co/datasets/llm-jp/hh-rlhf-12k-ja", + "project_name": "hh-rlhf-12k-ja", + "downloads": 326, "source": "Hugging Face", - "score": -0.10894692263222377, - "first_commit": "2024-03-06 03:30:25", - "latest_commit": "2024-03-06 21:46:11", + "score": -0.08933778870141348, + "first_commit": "2024-02-04 21:19:53", + "latest_commit": "2024-02-04 21:45:59", "languages": [], - "model_or_dataset": "model", - "model_size": 0.91, - "model_architectures": "CustomCLIPModel" + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null }, { - "description": "tokyotech-llm-Swallow-13b-instruct-v0.1-gguf tokyotech-llmさんが公開しているSwallow-13b-instruct-v0.1のggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/tokyotech-llm-Swallow-13b-instruct-v0.1-gguf", - "project_name": "tokyotech-llm-Swallow-13b-instruct-v0.1-gguf", - "downloads": 349, + "description": "Parakeet TDT-CTC 0.6B (ja) | | parakeet-tdt_ctc-0.6b-ja is an ASR model that transcribes Japanese speech with Punctuations.", + "url": "https://huggingface.co/nvidia/parakeet-tdt_ctc-0.6b-ja", + "project_name": "parakeet-tdt_ctc-0.6b-ja", + "downloads": 325, "source": "Hugging Face", - "score": -0.10896263398891799, - "first_commit": "2024-05-02 14:18:27", - "latest_commit": "2024-05-03 04:36:24", + "score": -0.08934839365194981, + "first_commit": "2024-05-13 15:39:30", + "latest_commit": "2024-05-17 17:20:17", "languages": [], "model_or_dataset": "model", - "model_size": 13.1, + "model_size": null, "model_architectures": null }, { "description": "ELYZA-japanese-CodeLlama-7b Model Description ELYZA-japanese-CodeLlama-7b は、 Code Llamaをベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。 ", "url": "https://huggingface.co/elyza/ELYZA-japanese-CodeLlama-7b-instruct", "project_name": "ELYZA-japanese-CodeLlama-7b-instruct", - "downloads": 348, + "downloads": 325, "source": "Hugging Face", - "score": -0.10897834534561221, + "score": -0.08934839365194981, "first_commit": "2023-11-07 12:04:07", "latest_commit": "2023-11-17 05:01:00", "languages": [], @@ -6458,166 +6617,194 @@ "model_architectures": "LlamaForCausalLM" }, { - "description": "line-corporation/japanese-large-lm-1.7b line-corporationさんが公開しているjapanese-large-lm-1.7bのgguf変換版です。 ", - "url": "https://huggingface.co/mmnga/line-corp-japanese-large-lm-1.7b-gguf", - "project_name": "line-corp-japanese-large-lm-1.7b-gguf", - "downloads": 346, + "description": "Mistral-Nemo-Instruct-2407-gguf mistralaiさんが公開しているMistral-Nemo-Instruct-2407のggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Mistral-Nemo-Instruct-2407-gguf", + "project_name": "Mistral-Nemo-Instruct-2407-gguf", + "downloads": 320, "source": "Hugging Face", - "score": -0.10900976805900064, - "first_commit": "2023-09-03 22:35:34", - "latest_commit": "2024-03-24 05:54:30", + "score": -0.08940141840463148, + "first_commit": "2024-07-22 13:28:13", + "latest_commit": "2024-07-22 17:25:48", "languages": [], "model_or_dataset": "model", - "model_size": 1.77, + "model_size": 12.2, "model_architectures": null }, { - "description": "luke-japanese luke-japanese is the Japanese version of LUKE (Language Understanding with Knowledge-based Embeddings), a pre-trained knowledge-enhanced contextualized representation of words and entities.", - "url": "https://huggingface.co/studio-ousia/luke-japanese-base", - "project_name": "luke-japanese-base", - "downloads": 345, + "description": "tokyotech-llm-Swallow-70b-instruct-v0.1-gguf tokyotech-llmさんが公開しているSwallow-70b-instruct-v0.1のggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/tokyotech-llm-Swallow-70b-instruct-v0.1-gguf", + "project_name": "tokyotech-llm-Swallow-70b-instruct-v0.1-gguf", + "downloads": 320, "source": "Hugging Face", - "score": -0.10902547941569486, - "first_commit": "2022-10-25 06:30:23", - "latest_commit": "2022-11-09 15:23:20", + "score": -0.08940141840463148, + "first_commit": "2024-05-03 09:00:00", + "latest_commit": "2024-05-04 06:52:16", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LukeForMaskedLM" + "model_size": 69.2, + "model_architectures": null }, { - "description": "lightblue-suzume-llama-3-8B-japanese-gguf lightblueさんが公開しているsuzume-llama-3-8B-japaneseのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/lightblue-suzume-llama-3-8B-japanese-gguf", - "project_name": "lightblue-suzume-llama-3-8B-japanese-gguf", - "downloads": 342, + "description": "What’s this?", + "url": "https://huggingface.co/globis-university/deberta-v3-japanese-xsmall", + "project_name": "deberta-v3-japanese-xsmall", + "downloads": 318, "source": "Hugging Face", - "score": -0.10907261348577751, - "first_commit": "2024-04-23 13:30:08", - "latest_commit": "2024-05-07 12:58:06", + "score": -0.08942262830570415, + "first_commit": "2023-09-21 16:12:53", + "latest_commit": "2024-07-05 05:48:15", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": null + "model_size": null, + "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "Llama-3-EZO-VLM-1 Based on SakanaAI/Llama-3-EvoVLM-JP-v2, it has been enhanced for Japanese usage through additional pre-training and instruction tuning.", - "url": "https://huggingface.co/AXCXEPT/Llama-3-EZO-VLM-1", - "project_name": "Llama-3-EZO-VLM-1", - "downloads": 338, + "description": "mt5_summarize_japanese (Japanese caption : 日本語の要約のモデル)", + "url": "https://huggingface.co/tsmatz/mt5_summarize_japanese", + "project_name": "mt5_summarize_japanese", + "downloads": 318, "source": "Hugging Face", - "score": -0.10913545891255438, - "first_commit": "2024-08-03 17:15:09", - "latest_commit": "2024-08-23 10:55:53", + "score": -0.08942262830570415, + "first_commit": "2022-11-26 10:51:27", + "latest_commit": "2024-07-12 00:01:31", "languages": [], "model_or_dataset": "model", - "model_size": 8.48, - "model_architectures": "LlavaForConditionalGeneration" + "model_size": 0.3, + "model_architectures": "MT5ForConditionalGeneration" }, { - "description": "rinna/japanese-gpt-neox-3.6b-instruction-ppo rinnaさんが公開しているjapanese-gpt-neox-3.6b-instruction-ppoのgguf変換版です。 ", - "url": "https://huggingface.co/mmnga/rinna-japanese-gpt-neox-3.6b-instruction-ppo-gguf", - "project_name": "rinna-japanese-gpt-neox-3.6b-instruction-ppo-gguf", - "downloads": 338, + "description": "[Llama-3.1-70B-EZO-1.1-it] Model Card モデル情報 / Model Information このモデルは、Meta AI の Llama 3.1 をベースに、日本語タスクでの性能を向上させるためにファインチューニングを行ったものです。", + "url": "https://huggingface.co/AXCXEPT/Llama-3.1-70B-EZO-1.1-it", + "project_name": "Llama-3.1-70B-EZO-1.1-it", + "downloads": 314, "source": "Hugging Face", - "score": -0.10913545891255438, - "first_commit": "2023-09-02 17:52:26", - "latest_commit": "2023-09-08 02:39:00", + "score": -0.08946504810784948, + "first_commit": "2024-07-29 01:35:35", + "latest_commit": "2024-08-23 10:52:31", "languages": [], "model_or_dataset": "model", - "model_size": 3.61, + "model_size": 70.6, + "model_architectures": "LlamaForCausalLM" + }, + { + "description": "ryota39-Phi-3-mini-4k-instruct-dpo-gguf ryota39さんが公開しているPhi-3-mini-4k-instruct-dpoのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/ryota39-Phi-3-mini-4k-instruct-dpo-gguf", + "project_name": "ryota39-Phi-3-mini-4k-instruct-dpo-gguf", + "downloads": 313, + "source": "Hugging Face", + "score": -0.08947565305838581, + "first_commit": "2024-04-29 14:27:31", + "latest_commit": "2024-04-29 16:53:45", + "languages": [], + "model_or_dataset": "model", + "model_size": 3.82, "model_architectures": null }, { - "description": "mt5_summarize_japanese (Japanese caption : 日本語の要約のモデル)", - "url": "https://huggingface.co/tsmatz/mt5_summarize_japanese", - "project_name": "mt5_summarize_japanese", - "downloads": 337, + "description": "lightblue-suzume-llama-3-8B-japanese-gguf lightblueさんが公開しているsuzume-llama-3-8B-japaneseのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/lightblue-suzume-llama-3-8B-japanese-gguf", + "project_name": "lightblue-suzume-llama-3-8B-japanese-gguf", + "downloads": 311, "source": "Hugging Face", - "score": -0.1091511702692486, - "first_commit": "2022-11-26 10:51:27", - "latest_commit": "2024-07-12 00:01:31", + "score": -0.08949686295945848, + "first_commit": "2024-04-23 13:30:08", + "latest_commit": "2024-05-07 12:58:06", "languages": [], "model_or_dataset": "model", - "model_size": 0.3, - "model_architectures": "MT5ForConditionalGeneration" + "model_size": 8.03, + "model_architectures": null }, { - "description": "Overview This dataset provides a convenient and user-friendly format of data from Aozora Bunko (青空文庫), a website that compiles public-domain books in Japan, ideal for Machine Learning applications.", - "url": "https://huggingface.co/datasets/globis-university/aozorabunko-clean", - "project_name": "aozorabunko-clean", - "downloads": 332, + "description": "Mistral-Nemo-Japanese-Instruct-2408 Model Description", + "url": "https://huggingface.co/cyberagent/Mistral-Nemo-Japanese-Instruct-2408", + "project_name": "Mistral-Nemo-Japanese-Instruct-2408", + "downloads": 310, "source": "Hugging Face", - "score": -0.10922972705271969, - "first_commit": "2023-06-26 13:31:28", - "latest_commit": "2023-10-27 13:22:32", + "score": -0.08950746790999482, + "first_commit": "2024-08-30 03:57:43", + "latest_commit": "2024-08-30 04:03:41", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_or_dataset": "model", + "model_size": 12.2, + "model_architectures": "MistralForCausalLM" + }, + { + "description": "tokyotech-llm-Swallow-MS-7b-instruct-v0.1-gguf tokyotech-llmさんが公開しているSwallow-MS-7b-instruct-v0.1のggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/tokyotech-llm-Swallow-MS-7b-instruct-v0.1-gguf", + "project_name": "tokyotech-llm-Swallow-MS-7b-instruct-v0.1-gguf", + "downloads": 309, + "source": "Hugging Face", + "score": -0.08951807286053115, + "first_commit": "2024-05-02 13:37:22", + "latest_commit": "2024-05-03 04:35:34", + "languages": [], + "model_or_dataset": "model", + "model_size": 7.33, "model_architectures": null }, { - "description": "t5-base-japanese-web (with Byte-fallback, 32K) Description megagonlabs/t5-base-japanese-web is a T5 (Text-to-Text Transfer Transformer) model pre-trained on Japanese web texts.", - "url": "https://huggingface.co/megagonlabs/t5-base-japanese-web", - "project_name": "t5-base-japanese-web", - "downloads": 331, + "description": "回答と回答が出てくるパラグラフ���与えると質問文を生成するモデル SEE: https://github.com/sonoisa/deep-question-generation 本モデルの作成ステップ概要 SQuAD 1.1を日本語に機械翻訳し、不正なデータをクレンジング（有効なデータは約半分）。", + "url": "https://huggingface.co/sonoisa/t5-base-japanese-question-generation", + "project_name": "t5-base-japanese-question-generation", + "downloads": 307, "source": "Hugging Face", - "score": -0.1092454384094139, - "first_commit": "2021-08-24 04:41:45", - "latest_commit": "2021-09-06 19:32:21", + "score": -0.08953928276160382, + "first_commit": "2021-04-03 14:08:55", + "latest_commit": "2022-03-11 02:50:33", "languages": [], "model_or_dataset": "model", "model_size": null, "model_architectures": "T5ForConditionalGeneration" }, { - "description": "hotchpotch/japanese-reranker-cross-encoder-small-v1 日本語で学習させた Reranker (CrossEncoder) シリーズです。 ", - "url": "https://huggingface.co/hotchpotch/japanese-reranker-cross-encoder-small-v1", - "project_name": "japanese-reranker-cross-encoder-small-v1", - "downloads": 330, + "description": "rinna/japanese-gpt-neox-3.6b-instruction-ppo rinnaさんが公開しているjapanese-gpt-neox-3.6b-instruction-ppoのgguf変換版です。 ", + "url": "https://huggingface.co/mmnga/rinna-japanese-gpt-neox-3.6b-instruction-ppo-gguf", + "project_name": "rinna-japanese-gpt-neox-3.6b-instruction-ppo-gguf", + "downloads": 300, "source": "Hugging Face", - "score": -0.10926114976610811, - "first_commit": "2024-03-28 04:31:45", - "latest_commit": "2024-04-01 02:39:19", + "score": -0.08961351741535815, + "first_commit": "2023-09-02 17:52:26", + "latest_commit": "2023-09-08 02:39:00", "languages": [], "model_or_dataset": "model", - "model_size": 0.11800000000000001, - "model_architectures": "XLMRobertaForSequenceClassification" + "model_size": 3.61, + "model_architectures": null }, { - "description": "rinna/japanese-gpt-neox-3.6b rinnaさんが公開しているjapanese-gpt-neox-3.6bのgguf変換版です。 ", - "url": "https://huggingface.co/mmnga/rinna-japanese-gpt-neox-3.6b-gguf", - "project_name": "rinna-japanese-gpt-neox-3.6b-gguf", - "downloads": 330, + "description": "What’s this?", + "url": "https://huggingface.co/globis-university/deberta-v3-japanese-base", + "project_name": "deberta-v3-japanese-base", + "downloads": 299, "source": "Hugging Face", - "score": -0.10926114976610811, - "first_commit": "2023-09-02 18:46:08", - "latest_commit": "2023-09-08 02:37:19", + "score": -0.0896241223658945, + "first_commit": "2023-09-21 16:19:31", + "latest_commit": "2024-07-05 05:49:13", "languages": [], "model_or_dataset": "model", - "model_size": 3.61, - "model_architectures": null + "model_size": null, + "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "This repository contains some GGUF quantizations of the VNTL Gemma 2 27B model.", - "url": "https://huggingface.co/lmg-anon/vntl-gemma2-27b-gguf", - "project_name": "vntl-gemma2-27b-gguf", - "downloads": 328, + "description": "Reflection-Llama-3.1-70B-gguf mattshumerさんが公開しているReflection-Llama-3.1-70Bのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Reflection-Llama-3.1-70B-gguf", + "project_name": "Reflection-Llama-3.1-70B-gguf", + "downloads": 299, "source": "Hugging Face", - "score": -0.10929257247949654, - "first_commit": "2024-07-07 00:28:06", - "latest_commit": "2024-07-08 16:13:54", + "score": -0.0896241223658945, + "first_commit": "2024-09-06 17:18:27", + "latest_commit": "2024-09-07 04:00:27", "languages": [], "model_or_dataset": "model", - "model_size": 27.2, + "model_size": 70.6, "model_architectures": null }, { "description": "tokyotech-llm様の Llama-3-Swallow-8B-Instruct-v0.1 をGGUF形式に変換したものです。 ", "url": "https://huggingface.co/MCZK/Llama-3-Swallow-8B-Instruct-v0.1-GGUF", "project_name": "Llama-3-Swallow-8B-Instruct-v0.1-GGUF", - "downloads": 326, + "downloads": 297, "source": "Hugging Face", - "score": -0.10932399519288498, + "score": -0.08964533226696716, "first_commit": "2024-07-01 11:45:22", "latest_commit": "2024-07-01 17:54:05", "languages": [], @@ -6626,180 +6813,194 @@ "model_architectures": null }, { - "description": "[Llama-3.1-70B-EZO-1.1-it] Model Card モデル情報 / Model Information このモデルは、Meta AI の Llama 3.1 をベースに、日本語タスクでの性能を向上させるためにファインチューニングを行ったものです。", - "url": "https://huggingface.co/AXCXEPT/Llama-3.1-70B-EZO-1.1-it", - "project_name": "Llama-3.1-70B-EZO-1.1-it", - "downloads": 326, + "description": "HODACHI-EZO-Humanities-9B-gemma-2-it-gguf HODACHIさんが公開しているEZO-Humanities-9B-gemma-2-itのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/HODACHI-EZO-Humanities-9B-gemma-2-it-gguf", + "project_name": "HODACHI-EZO-Humanities-9B-gemma-2-it-gguf", + "downloads": 290, "source": "Hugging Face", - "score": -0.10932399519288498, - "first_commit": "2024-07-29 01:35:35", - "latest_commit": "2024-08-23 10:52:31", + "score": -0.0897195669207215, + "first_commit": "2024-07-15 15:43:00", + "latest_commit": "2024-07-15 17:01:09", "languages": [], "model_or_dataset": "model", - "model_size": 70.6, - "model_architectures": "LlamaForCausalLM" + "model_size": 9.24, + "model_architectures": null }, { - "description": "YuisekinAIEvol-Mistral-7B-ja-math-v0.1.1-gguf yuisekiさんが公開しているYuisekinAIEvol-Mistral-7B-ja-math-v0.1.1のggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/YuisekinAIEvol-Mistral-7B-ja-math-v0.1.1-gguf", - "project_name": "YuisekinAIEvol-Mistral-7B-ja-math-v0.1.1-gguf", - "downloads": 323, + "description": "BERT large Japanese (character-level tokenization with whole word masking, CC-100 and jawiki-20230102)", + "url": "https://huggingface.co/tohoku-nlp/bert-large-japanese-char-v2", + "project_name": "bert-large-japanese-char-v2", + "downloads": 288, "source": "Hugging Face", - "score": -0.10937112926296763, - "first_commit": "2024-04-29 14:18:07", - "latest_commit": "2024-04-29 15:52:08", + "score": -0.08974077682179417, + "first_commit": "2023-05-19 00:48:06", + "latest_commit": "2023-05-19 00:54:57", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": null + "model_size": null, + "model_architectures": "BertForPreTraining" }, { - "description": "c4ai-command-r-plus-gguf CohereForAIさんが公開しているc4ai-command-r-plusのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/c4ai-command-r-plus-gguf", - "project_name": "c4ai-command-r-plus-gguf", - "downloads": 321, + "description": "Model Card for Japanese character-level GPT-2 Small Model description This is a Japanese character-level GPT-2 Small (90M parameters) language model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.", + "url": "https://huggingface.co/ku-nlp/gpt2-small-japanese-char", + "project_name": "gpt2-small-japanese-char", + "downloads": 281, "source": "Hugging Face", - "score": -0.10940255197635607, - "first_commit": "2024-04-22 14:46:41", - "latest_commit": "2024-04-23 16:13:37", + "score": -0.0898150114755485, + "first_commit": "2023-04-18 08:24:55", + "latest_commit": "2023-05-08 10:08:13", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": null + "model_size": 0.10300000000000001, + "model_architectures": "GPT2LMHeadModel" }, { - "description": "luke-japanese luke-japanese is the Japanese version of LUKE (Language Understanding with Knowledge-based Embeddings), a pre-trained knowledge-enhanced contextualized representation of words and entities.", - "url": "https://huggingface.co/studio-ousia/luke-japanese-base-lite", - "project_name": "luke-japanese-base-lite", - "downloads": 316, + "description": "rinna/japanese-gpt-neox-3.6b rinnaさんが公開しているjapanese-gpt-neox-3.6bのgguf変換版です。 ", + "url": "https://huggingface.co/mmnga/rinna-japanese-gpt-neox-3.6b-gguf", + "project_name": "rinna-japanese-gpt-neox-3.6b-gguf", + "downloads": 279, "source": "Hugging Face", - "score": -0.10948110875982715, - "first_commit": "2022-10-25 09:27:16", - "latest_commit": "2022-11-09 15:22:22", + "score": -0.08983622137662117, + "first_commit": "2023-09-02 18:46:08", + "latest_commit": "2023-09-08 02:37:19", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LukeForMaskedLM" + "model_size": 3.61, + "model_architectures": null }, { - "description": "QuantFactory/Llama3.1-ArrowSE-v0.4-GGUF This is quantized version of DataPilot/Llama3.1-ArrowSE-v0.4 created using llama.cpp Original Model Card 概要 このモデルはllama3.1-8B-instructをもとに日本語性能を高めることを目的にMergekit&ファインチューニングを用いて作成されました。 ", - "url": "https://huggingface.co/QuantFactory/Llama3.1-ArrowSE-v0.4-GGUF", - "project_name": "Llama3.1-ArrowSE-v0.4-GGUF", - "downloads": 316, + "description": "JA-VG-VQA-500 Dataset Description JA-VG-VQA-500 is a 500-sample subset of Japanese Visual Genome VQA dataset.", + "url": "https://huggingface.co/datasets/SakanaAI/JA-VG-VQA-500", + "project_name": "JA-VG-VQA-500", + "downloads": 275, "source": "Hugging Face", - "score": -0.10948110875982715, - "first_commit": "2024-07-28 06:17:48", - "latest_commit": "2024-07-28 06:57:40", + "score": -0.08987864117876651, + "first_commit": "2024-03-21 09:51:10", + "latest_commit": "2024-05-14 04:11:31", "languages": [], - "model_or_dataset": "model", - "model_size": 8.03, + "model_or_dataset": "dataset", + "model_size": null, "model_architectures": null }, { - "description": "recruit-jp/japanese-typo-detector-roberta-base モデルの概要 日本語の文章を入力すると各文字ごとに誤字脱字である確率を出力します 各ラベルの意味は以下の通りです id label meaning 0 OK 誤字なし 1 deletion 1文字の抜け 2 insertion_a 余分な1文字の挿入 3 insertion_b 直前の文字列と一致する２文字以上の余分な文字の挿入 4 kanji-conversion_a 同一の読みを持つ漢字の入れ替え（誤変換） 5 kanji-conversion_b 近い読みを持つ漢字の入れ替え（誤変換） 6 substitution 1文字の入れ替え 7 transposition 隣接する２文字間の転置 8 others その他の入力誤り 誤り種類の詳細については学習データセットの元論文をご参照ください 日本語 Wikipedia の編集履歴に基づく 入力誤りデータセットと訂正システムの改良 その他、モデルの詳細については当社ブログ記事をご参照ください 誤字脱字検出モデルをHugging Face Hubに公開しました (Re", - "url": "https://huggingface.co/recruit-jp/japanese-typo-detector-roberta-base", - "project_name": "japanese-typo-detector-roberta-base", - "downloads": 315, + "description": "ElanMT ElanMT-BT-ja-en is a Japanese to English translation model developed by ELAN MITSUA Project / Abstract Engine.", + "url": "https://huggingface.co/Mitsua/elan-mt-bt-ja-en", + "project_name": "elan-mt-bt-ja-en", + "downloads": 272, "source": "Hugging Face", - "score": -0.10949682011652137, - "first_commit": "2023-11-09 06:27:40", - "latest_commit": "2023-12-21 03:07:31", + "score": -0.08991045603037551, + "first_commit": "2024-05-20 01:56:12", + "latest_commit": "2024-05-20 01:56:57", "languages": [], "model_or_dataset": "model", - "model_size": 0.0996, - "model_architectures": "RobertaForTokenClassification" + "model_size": 0.0606, + "model_architectures": "MarianMTModel" }, { - "description": "line-corporation/japanese-large-lm-1.7b-instruction-sft line-corporationさんが公開しているjapanese-large-lm-1.7b-instruction-sftのgguf変換版です。 ", - "url": "https://huggingface.co/mmnga/line-corp-japanese-large-lm-1.7b-instruction-sft-gguf", - "project_name": "line-corp-japanese-large-lm-1.7b-instruction-sft-gguf", - "downloads": 313, + "description": "zenz-v1 Checkpoints zenz-v1 is a language model specialized for kana-kanji conversion tasks based on the GPT-2 architecture.", + "url": "https://huggingface.co/Miwa-Keita/zenz-v1-checkpoints", + "project_name": "zenz-v1-checkpoints", + "downloads": 272, "source": "Hugging Face", - "score": -0.1095282428299098, - "first_commit": "2023-09-03 22:30:23", - "latest_commit": "2024-03-24 05:54:56", + "score": -0.08991045603037551, + "first_commit": "2024-06-28 14:26:33", + "latest_commit": "2024-06-28 14:53:43", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "GPT2LMHeadModel" }, { - "description": "What’s this?", - "url": "https://huggingface.co/globis-university/deberta-v3-japanese-xsmall", - "project_name": "deberta-v3-japanese-xsmall", - "downloads": 307, + "description": "JaQuAD is developed to provide a SQuAD-like QA dataset in Japanese.", + "url": "https://huggingface.co/datasets/SkelterLabsInc/JaQuAD", + "project_name": "JaQuAD", + "downloads": 272, "source": "Hugging Face", - "score": -0.10962251097007511, - "first_commit": "2023-09-21 16:12:53", - "latest_commit": "2024-07-05 05:48:15", + "score": -0.08991045603037551, + "first_commit": "2022-01-26 01:34:38", + "latest_commit": "2022-10-25 09:06:40", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "DebertaV2ForTokenClassification" + "model_architectures": null }, { - "description": "ryota39-Phi-3-mini-4k-instruct-dpo-gguf ryota39さんが公開しているPhi-3-mini-4k-instruct-dpoのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/ryota39-Phi-3-mini-4k-instruct-dpo-gguf", - "project_name": "ryota39-Phi-3-mini-4k-instruct-dpo-gguf", - "downloads": 306, + "description": "DataPilot-ArrowPro-7B-RobinHood-gguf DataPilotさんが公開しているArrowPro-7B-RobinHoodのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/DataPilot-ArrowPro-7B-RobinHood-gguf", + "project_name": "DataPilot-ArrowPro-7B-RobinHood-gguf", + "downloads": 271, "source": "Hugging Face", - "score": -0.10963822232676933, - "first_commit": "2024-04-29 14:27:31", - "latest_commit": "2024-04-29 16:53:45", + "score": -0.08992106098091183, + "first_commit": "2024-05-11 07:22:37", + "latest_commit": "2024-05-11 13:43:09", "languages": [], "model_or_dataset": "model", - "model_size": 3.82, + "model_size": 7.24, "model_architectures": null }, { - "description": "HODACHI様の EZO-Common-T2-2B-gemma-2-it をGGUF形式に変換したものです。 ", - "url": "https://huggingface.co/MCZK/EZO-Common-T2-2B-gemma-2-it-GGUF", - "project_name": "EZO-Common-T2-2B-gemma-2-it-GGUF", - "downloads": 299, + "description": "Model Card for Tanrei/GPTSAN-japanese General-purpose Swich transformer based Japanese language model GPTSAN has some unique features.", + "url": "https://huggingface.co/Tanrei/GPTSAN-japanese", + "project_name": "GPTSAN-japanese", + "downloads": 270, "source": "Hugging Face", - "score": -0.10974820182362885, - "first_commit": "2024-08-01 11:38:48", - "latest_commit": "2024-08-01 13:42:20", + "score": -0.08993166593144818, + "first_commit": "2023-01-06 05:41:12", + "latest_commit": "2023-04-21 19:04:49", "languages": [], "model_or_dataset": "model", - "model_size": 2.61, - "model_architectures": null + "model_size": 2.78, + "model_architectures": "GPTSanJapaneseForConditionalGeneration" }, { - "description": "Dataset.", - "url": "https://huggingface.co/datasets/hpprc/jsick", - "project_name": "jsick", - "downloads": 294, + "description": "Model card for model ID", + "url": "https://huggingface.co/retrieva-jp/t5-small-short", + "project_name": "t5-small-short", + "downloads": 267, "source": "Hugging Face", - "score": -0.10982675860709994, - "first_commit": "2023-04-08 16:02:06", - "latest_commit": "2023-04-11 15:18:09", + "score": -0.08996348078305717, + "first_commit": "2023-04-25 04:37:20", + "latest_commit": "2023-05-10 09:55:39", "languages": [], - "model_or_dataset": "dataset", + "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "T5ForConditionalGeneration" }, { - "description": "tokyotech-llm-Swallow-MS-7b-instruct-v0.1-gguf tokyotech-llmさんが公開しているSwallow-MS-7b-instruct-v0.1のggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/tokyotech-llm-Swallow-MS-7b-instruct-v0.1-gguf", - "project_name": "tokyotech-llm-Swallow-MS-7b-instruct-v0.1-gguf", - "downloads": 292, + "description": "Ninja-v1-128k-gguf Local-Novel-LLM-projectさんが公開しているNinja-v1-128kのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Ninja-v1-128k-gguf", + "project_name": "Ninja-v1-128k-gguf", + "downloads": 266, "source": "Hugging Face", - "score": -0.10985818132048837, - "first_commit": "2024-05-02 13:37:22", - "latest_commit": "2024-05-03 04:35:34", + "score": -0.08997408573359351, + "first_commit": "2024-05-01 17:48:06", + "latest_commit": "2024-05-04 13:25:20", "languages": [], "model_or_dataset": "model", - "model_size": 7.33, + "model_size": 7.24, "model_architectures": null }, + { + "description": "XLNet-japanese Model description This model require Mecab and senetencepiece with XLNetTokenizer.", + "url": "https://huggingface.co/hajime9652/xlnet-japanese", + "project_name": "xlnet-japanese", + "downloads": 265, + "source": "Hugging Face", + "score": -0.08998469068412984, + "first_commit": "2021-04-01 03:12:11", + "latest_commit": "2023-01-05 04:28:36", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "XLNetLMHeadModel" + }, { "description": "Oumuamua-7b-RP GGUF版はこちら/Click here for the GGUF version 概要 This is a merge of pre-trained language models created using mergekit. ", "url": "https://huggingface.co/Aratako/Oumuamua-7b-RP", "project_name": "Oumuamua-7b-RP", - "downloads": 292, + "downloads": 263, "source": "Hugging Face", - "score": -0.10985818132048837, + "score": -0.09000590058520251, "first_commit": "2024-06-23 12:30:16", "latest_commit": "2024-06-23 17:06:53", "languages": [], @@ -6808,166 +7009,152 @@ "model_architectures": "MistralForCausalLM" }, { - "description": "tokyotech-llm-Swallow-70b-instruct-v0.1-gguf tokyotech-llmさんが公開しているSwallow-70b-instruct-v0.1のggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/tokyotech-llm-Swallow-70b-instruct-v0.1-gguf", - "project_name": "tokyotech-llm-Swallow-70b-instruct-v0.1-gguf", - "downloads": 289, + "description": "Tanuki-8B-dpo-v1.0-GGUF 概要 GENIAC 松尾研 LLM開発プロジェクトで開発されたLLMであるweblab-GENIAC/Tanuki-8B-dpo-v1.0-4kのGGUF量子化モデルです。", + "url": "https://huggingface.co/team-hatakeyama-phase2/Tanuki-8B-dpo-v1.0-4k-GGUF", + "project_name": "Tanuki-8B-dpo-v1.0-4k-GGUF", + "downloads": 259, "source": "Hugging Face", - "score": -0.10990531539057102, - "first_commit": "2024-05-03 09:00:00", - "latest_commit": "2024-05-04 06:52:16", + "score": -0.09004832038734785, + "first_commit": "2024-08-16 12:39:31", + "latest_commit": "2024-08-27 18:05:25", "languages": [], "model_or_dataset": "model", - "model_size": 69.2, + "model_size": 7.51, "model_architectures": null }, { - "description": "Dataset Preprocessing Supported Tasks and Leaderboards Languages 注釈はすべて日本語を主要言語としています。 ", - "url": "https://huggingface.co/datasets/shunk031/jsnli", - "project_name": "jsnli", - "downloads": 288, + "description": "This repository contains some GGUF quantizations of the VNTL Gemma 2 27B model.", + "url": "https://huggingface.co/lmg-anon/vntl-gemma2-27b-gguf", + "project_name": "vntl-gemma2-27b-gguf", + "downloads": 259, "source": "Hugging Face", - "score": -0.10992102674726524, - "first_commit": "2022-12-01 01:31:32", - "latest_commit": "2022-12-12 16:36:58", + "score": -0.09004832038734785, + "first_commit": "2024-07-07 00:28:06", + "latest_commit": "2024-07-08 16:13:54", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_or_dataset": "model", + "model_size": 27.2, "model_architectures": null }, { - "description": "JA-VG-VQA-500 Dataset Description JA-VG-VQA-500 is a 500-sample subset of Japanese Visual Genome VQA dataset.", - "url": "https://huggingface.co/datasets/SakanaAI/JA-VG-VQA-500", - "project_name": "JA-VG-VQA-500", - "downloads": 282, + "description": "pfnet-nekomata-14b-pfn-qfin-inst-merge-gguf pfnetさんが公開しているnekomata-14b-pfn-qfin-inst-mergeのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/pfnet-nekomata-14b-pfn-qfin-inst-merge-gguf", + "project_name": "pfnet-nekomata-14b-pfn-qfin-inst-merge-gguf", + "downloads": 258, "source": "Hugging Face", - "score": -0.11001529488743053, - "first_commit": "2024-03-21 09:51:10", - "latest_commit": "2024-05-14 04:11:31", + "score": -0.09005892533788418, + "first_commit": "2024-04-23 14:53:08", + "latest_commit": "2024-04-24 14:39:32", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_or_dataset": "model", + "model_size": 14.2, "model_architectures": null }, { - "description": "Japanese Natural Language Inference Model", - "url": "https://huggingface.co/cyberagent/xlm-roberta-large-jnli-jsick", - "project_name": "xlm-roberta-large-jnli-jsick", - "downloads": 280, + "description": "hotchpotch/japanese-reranker-cross-encoder-small-v1 日本語で学習させた Reranker (CrossEncoder) シリーズです。 ", + "url": "https://huggingface.co/hotchpotch/japanese-reranker-cross-encoder-small-v1", + "project_name": "japanese-reranker-cross-encoder-small-v1", + "downloads": 256, "source": "Hugging Face", - "score": -0.11004671760081897, - "first_commit": "2022-12-23 10:51:12", - "latest_commit": "2022-12-23 10:51:12", + "score": -0.09008013523895685, + "first_commit": "2024-03-28 04:31:45", + "latest_commit": "2024-04-01 02:39:19", "languages": [], "model_or_dataset": "model", - "model_size": null, + "model_size": 0.11800000000000001, "model_architectures": "XLMRobertaForSequenceClassification" }, { - "description": "Ninja-v1-RP-expressive-GGUF 概要 Aratako/Ninja-v1-RP-expressive-v2の量子化済みGGUF版です。", - "url": "https://huggingface.co/Aratako/Ninja-v1-RP-expressive-v2-GGUF", - "project_name": "Ninja-v1-RP-expressive-v2-GGUF", - "downloads": 278, + "description": "By clicking \"Agree\", you agree to the License Agreement and acknowledge Stability AI's Privacy Policy.", + "url": "https://huggingface.co/stabilityai/japanese-stable-diffusion-xl", + "project_name": "japanese-stable-diffusion-xl", + "downloads": 256, "source": "Hugging Face", - "score": -0.1100781403142074, - "first_commit": "2024-05-26 06:09:57", - "latest_commit": "2024-05-26 15:22:01", + "score": -0.09008013523895685, + "first_commit": null, + "latest_commit": null, "languages": [], "model_or_dataset": "model", - "model_size": 7.24, + "model_size": null, "model_architectures": null }, { - "description": "Model Card for Japanese BART large Model description", - "url": "https://huggingface.co/ku-nlp/bart-large-japanese", - "project_name": "bart-large-japanese", - "downloads": 276, + "description": "日本語向け Llama 3 8B はじめに このリポジトリはLlama 3を日本語化しようとしたモデルのリポジトリです。", + "url": "https://huggingface.co/alfredplpl/Llama-3-8B-Instruct-Ja", + "project_name": "Llama-3-8B-Instruct-Ja", + "downloads": 252, "source": "Hugging Face", - "score": -0.11010956302759584, - "first_commit": "2023-05-09 07:44:59", - "latest_commit": "2023-05-12 11:05:03", + "score": -0.09012255504110218, + "first_commit": "2024-04-22 05:14:33", + "latest_commit": "2024-05-01 19:16:01", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "MBartForConditionalGeneration" + "model_size": 8.03, + "model_architectures": "LlamaForCausalLM" }, { - "description": "pfnet-Llama3-Preferred-MedSwallow-70B-gguf pfnetさんが公開しているLlama3-Preferred-MedSwallow-70Bのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/pfnet-Llama3-Preferred-MedSwallow-70B-gguf", - "project_name": "pfnet-Llama3-Preferred-MedSwallow-70B-gguf", - "downloads": 275, + "description": "読み込み方 from datasets import load_dataset dataset = load_dataset(\"YANS-official/ogiri-test\", split=\"test\") 概要 大喜利投稿サイトBoketeのクロールデータです。", + "url": "https://huggingface.co/datasets/YANS-official/ogiri-test", + "project_name": "ogiri-test", + "downloads": 251, "source": "Hugging Face", - "score": -0.11012527438429005, - "first_commit": "2024-07-18 15:45:16", - "latest_commit": "2024-07-19 09:14:38", + "score": -0.09013315999163851, + "first_commit": "2024-09-03 15:08:05", + "latest_commit": "2024-09-09 05:53:54", "languages": [], - "model_or_dataset": "model", - "model_size": 70.6, + "model_or_dataset": "dataset", + "model_size": null, "model_architectures": null }, { - "description": "zenz-v1 Checkpoints zenz-v1 is a language model specialized for kana-kanji conversion tasks based on the GPT-2 architecture.", - "url": "https://huggingface.co/Miwa-Keita/zenz-v1-checkpoints", - "project_name": "zenz-v1-checkpoints", - "downloads": 273, + "description": "Local-Novel-LLM-project様の Assistance をGGUF形式に変換したものです。 ", + "url": "https://huggingface.co/MCZK/Assistance-7B-GGUF", + "project_name": "Assistance-7B-GGUF", + "downloads": 247, "source": "Hugging Face", - "score": -0.11015669709767849, - "first_commit": "2024-06-28 14:26:33", - "latest_commit": "2024-06-28 14:53:43", + "score": -0.09017557979378385, + "first_commit": "2024-05-03 12:16:29", + "latest_commit": "2024-05-04 07:48:41", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "GPT2LMHeadModel" + "model_size": 7.24, + "model_architectures": null }, { - "description": "What’s this?", - "url": "https://huggingface.co/globis-university/deberta-v3-japanese-large", - "project_name": "deberta-v3-japanese-large", - "downloads": 269, + "description": "Model card for model ID", + "url": "https://huggingface.co/retrieva-jp/t5-large-long", + "project_name": "t5-large-long", + "downloads": 246, "source": "Hugging Face", - "score": -0.11021954252445536, - "first_commit": "2023-09-21 16:15:15", - "latest_commit": "2024-07-05 05:50:06", + "score": -0.09018618474432019, + "first_commit": "2023-04-26 08:33:12", + "latest_commit": "2023-05-10 10:00:35", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForTokenClassification" + "model_architectures": "T5ForConditionalGeneration" }, { - "description": "This is a Japanese sentence-LUKE model.", - "url": "https://huggingface.co/cheonboy/sentence_embedding_japanese", - "project_name": "sentence_embedding_japanese", - "downloads": 268, + "description": "Additional pretrained BERT base Japanese finance This is a BERT model pretrained on texts in the Japanese language.", + "url": "https://huggingface.co/izumi-lab/bert-base-japanese-fin-additional", + "project_name": "bert-base-japanese-fin-additional", + "downloads": 244, "source": "Hugging Face", - "score": -0.11023525388114958, - "first_commit": "2023-10-05 05:10:25", - "latest_commit": "2023-10-05 05:13:09", + "score": -0.09020739464539286, + "first_commit": "2022-03-11 17:41:11", + "latest_commit": "2022-12-09 00:40:25", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "LukeModel" - }, - { - "description": "Dataset Summary This is the Business Scene Dialogue (BSD) dataset, a Japanese-English parallel corpus containing written conversations in various business scenarios.", - "url": "https://huggingface.co/datasets/ryo0634/bsd_ja_en", - "project_name": "bsd_ja_en", - "downloads": 267, - "source": "Hugging Face", - "score": -0.11025096523784379, - "first_commit": "2022-01-25 16:35:02", - "latest_commit": "2024-01-11 07:36:44", - "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null + "model_architectures": "BertForPreTraining" }, { "description": "ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF", "url": "https://huggingface.co/QuantFactory/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF", "project_name": "ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF", - "downloads": 264, + "downloads": 243, "source": "Hugging Face", - "score": -0.11029809930792644, + "score": -0.09021799959592919, "first_commit": "2024-07-05 05:56:09", "latest_commit": "2024-07-13 13:29:45", "languages": [], @@ -6976,68 +7163,40 @@ "model_architectures": null }, { - "description": "Githubリポジトリstockmarkteam/ner-wikipedia-datasetで公開されているデータセットを利用しています。", - "url": "https://huggingface.co/datasets/llm-book/ner-wikipedia-dataset", - "project_name": "ner-wikipedia-dataset", - "downloads": 264, - "source": "Hugging Face", - "score": -0.11029809930792644, - "first_commit": "2023-04-15 10:43:21", - "latest_commit": "2023-12-12 11:25:51", - "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null - }, - { - "description": "JaQuAD is developed to provide a SQuAD-like QA dataset in Japanese.", - "url": "https://huggingface.co/datasets/SkelterLabsInc/JaQuAD", - "project_name": "JaQuAD", - "downloads": 263, - "source": "Hugging Face", - "score": -0.11031381066462066, - "first_commit": "2022-01-26 01:34:38", - "latest_commit": "2022-10-25 09:06:40", - "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null - }, - { - "description": "OcuteusのGGUF版です。 ", - "url": "https://huggingface.co/Local-Novel-LLM-project/Ocuteus-v1-gguf", - "project_name": "Ocuteus-v1-gguf", - "downloads": 262, + "description": "SpeechT5 (TTS task) for Japanese SpeechT5 model fine-tuned for Japanese speech synthesis (text-to-speech)", + "url": "https://huggingface.co/esnya/japanese_speecht5_tts", + "project_name": "japanese_speecht5_tts", + "downloads": 241, "source": "Hugging Face", - "score": -0.11032952202131488, - "first_commit": "2024-05-07 09:57:49", - "latest_commit": "2024-05-10 06:18:35", + "score": -0.09023920949700186, + "first_commit": "2023-08-08 18:37:40", + "latest_commit": "2023-08-09 09:25:38", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": null + "model_size": 0.14400000000000002, + "model_architectures": "SpeechT5ForTextToSpeech" }, { - "description": "DataPilot-ArrowPro-7B-RobinHood-gguf DataPilotさんが公開しているArrowPro-7B-RobinHoodのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/DataPilot-ArrowPro-7B-RobinHood-gguf", - "project_name": "DataPilot-ArrowPro-7B-RobinHood-gguf", - "downloads": 262, + "description": "BERT small Japanese finance This is a BERT model pretrained on texts in the Japanese language.", + "url": "https://huggingface.co/izumi-lab/bert-small-japanese", + "project_name": "bert-small-japanese", + "downloads": 241, "source": "Hugging Face", - "score": -0.11032952202131488, - "first_commit": "2024-05-11 07:22:37", - "latest_commit": "2024-05-11 13:43:09", + "score": -0.09023920949700186, + "first_commit": "2021-10-04 13:09:36", + "latest_commit": "2022-12-09 00:40:57", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": null + "model_size": null, + "model_architectures": "BertForMaskedLM" }, { "description": "Japanese GPT2 Lyric Model Model description", "url": "https://huggingface.co/skytnt/gpt2-japanese-lyric-small", "project_name": "gpt2-japanese-lyric-small", - "downloads": 259, + "downloads": 241, "source": "Hugging Face", - "score": -0.11037665609139753, + "score": -0.09023920949700186, "first_commit": "2022-04-21 04:25:18", "latest_commit": "2023-10-23 12:46:36", "languages": [], @@ -7046,68 +7205,54 @@ "model_architectures": "GPT2LMHeadModel" }, { - "description": "Ninja-v1-128k-gguf Local-Novel-LLM-projectさんが公開しているNinja-v1-128kのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Ninja-v1-128k-gguf", - "project_name": "Ninja-v1-128k-gguf", - "downloads": 249, + "description": "alfredplpl-Llama-3-8B-Instruct-Ja-gguf alfredplplさんが公開しているLlama-3-8B-Instruct-Jaのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/alfredplpl-Llama-3-8B-Instruct-Ja-gguf", + "project_name": "alfredplpl-Llama-3-8B-Instruct-Ja-gguf", + "downloads": 239, "source": "Hugging Face", - "score": -0.1105337696583397, - "first_commit": "2024-05-01 17:48:06", - "latest_commit": "2024-05-04 13:25:20", + "score": -0.09026041939807453, + "first_commit": "2024-04-23 14:18:57", + "latest_commit": "2024-04-23 15:24:47", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, + "model_size": 8.03, "model_architectures": null }, { - "description": "By clicking \"Agree\", you agree to the License Agreement and acknowledge Stability AI's Privacy Policy.", - "url": "https://huggingface.co/stabilityai/japanese-stable-diffusion-xl", - "project_name": "japanese-stable-diffusion-xl", - "downloads": 243, + "description": "モデル説明 (model explanation) CoolJapanDiffusion 2.1.1とWaifuDiffusion 1.4 anime epoch2のマージ。", + "url": "https://huggingface.co/ThePioneer/CoolerWaifuDiffusion", + "project_name": "CoolerWaifuDiffusion", + "downloads": 236, "source": "Hugging Face", - "score": -0.110628037798505, - "first_commit": null, - "latest_commit": null, + "score": -0.09029223424968352, + "first_commit": "2023-01-20 23:52:39", + "latest_commit": "2023-01-22 19:16:59", "languages": [], "model_or_dataset": "model", "model_size": null, "model_architectures": null }, { - "description": "pfnet-nekomata-14b-pfn-qfin-inst-merge-gguf pfnetさんが公開しているnekomata-14b-pfn-qfin-inst-mergeのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/pfnet-nekomata-14b-pfn-qfin-inst-merge-gguf", - "project_name": "pfnet-nekomata-14b-pfn-qfin-inst-merge-gguf", - "downloads": 242, + "description": "tokyotech-llm-Swallow-7b-instruct-v0.1-gguf tokyotech-llmさんが公開しているSwallow-7b-instruct-v0.1のggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/tokyotech-llm-Swallow-7b-instruct-v0.1-gguf", + "project_name": "tokyotech-llm-Swallow-7b-instruct-v0.1-gguf", + "downloads": 236, "source": "Hugging Face", - "score": -0.11064374915519921, - "first_commit": "2024-04-23 14:53:08", - "latest_commit": "2024-04-24 14:39:32", + "score": -0.09029223424968352, + "first_commit": "2024-05-03 04:09:27", + "latest_commit": "2024-05-03 04:53:43", "languages": [], "model_or_dataset": "model", - "model_size": 14.2, - "model_architectures": null - }, - { - "description": "Dataset Details Dataset Type:Japanese LLaVA Instruct 150K is a localized version of the original LLaVA Visual Instruct 150K dataset.", - "url": "https://huggingface.co/datasets/turing-motors/LLaVA-Instruct-150K-JA", - "project_name": "LLaVA-Instruct-150K-JA", - "downloads": 242, - "source": "Hugging Face", - "score": -0.11064374915519921, - "first_commit": null, - "latest_commit": null, - "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_size": 6.83, "model_architectures": null }, { "description": "※llama.cpp Releases b3428(7/21)", "url": "https://huggingface.co/MCZK/EZO-Humanities-9B-gemma-2-it-GGUF", "project_name": "EZO-Humanities-9B-gemma-2-it-GGUF", - "downloads": 241, + "downloads": 234, "source": "Hugging Face", - "score": -0.11065946051189343, + "score": -0.09031344415075619, "first_commit": "2024-07-10 22:02:03", "latest_commit": "2024-07-21 18:11:21", "languages": [], @@ -7116,68 +7261,26 @@ "model_architectures": null }, { - "description": "XLNet-japanese Model description This model require Mecab and senetencepiece with XLNetTokenizer.", - "url": "https://huggingface.co/hajime9652/xlnet-japanese", - "project_name": "xlnet-japanese", - "downloads": 240, - "source": "Hugging Face", - "score": -0.11067517186858765, - "first_commit": "2021-04-01 03:12:11", - "latest_commit": "2023-01-05 04:28:36", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "XLNetLMHeadModel" - }, - { - "description": "日本語向け Llama 3 8B はじめに このリポジトリはLlama 3を日本語化しようとしたモデルのリポジトリです。", - "url": "https://huggingface.co/alfredplpl/Llama-3-8B-Instruct-Ja", - "project_name": "Llama-3-8B-Instruct-Ja", - "downloads": 240, - "source": "Hugging Face", - "score": -0.11067517186858765, - "first_commit": "2024-04-22 05:14:33", - "latest_commit": "2024-05-01 19:16:01", - "languages": [], - "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": "LlamaForCausalLM" - }, - { - "description": "Model card for model ID", - "url": "https://huggingface.co/retrieva-jp/t5-large-short", - "project_name": "t5-large-short", - "downloads": 239, + "description": "Model Trained Using AutoNLP Problem type: Binary Classification Model ID: 59362 Validation Metrics Loss: 0.13092292845249176 Accuracy: 0.9527127414314258 Precision: 0.9634070704982427 Recall: 0.9842171959602166 AUC: 0.9667289746092403 F1: 0.9737009564152002 Usage You can use cURL to access this model: $ curl -X POST -H \"Authorization: Bearer YOUR_API_KEY\" -H \"Content-Type: application/json\" -d '{\"inputs\": \"I love AutoNLP\"}' https://api-inference.huggingface.co/models/abhishek/autonlp-japanese-sentiment-5936", + "url": "https://huggingface.co/abhishek/autonlp-japanese-sentiment-59362", + "project_name": "autonlp-japanese-sentiment-59362", + "downloads": 233, "source": "Hugging Face", - "score": -0.11069088322528187, - "first_commit": "2023-04-26 08:18:58", - "latest_commit": "2023-05-10 10:00:54", + "score": -0.09032404910129253, + "first_commit": "2021-04-21 11:28:11", + "latest_commit": "2021-05-18 22:55:03", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "T5ForConditionalGeneration" - }, - { - "description": "tokyotech-llm-Swallow-7b-instruct-v0.1-gguf tokyotech-llmさんが公開しているSwallow-7b-instruct-v0.1のggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/tokyotech-llm-Swallow-7b-instruct-v0.1-gguf", - "project_name": "tokyotech-llm-Swallow-7b-instruct-v0.1-gguf", - "downloads": 238, - "source": "Hugging Face", - "score": -0.11070659458197608, - "first_commit": "2024-05-03 04:09:27", - "latest_commit": "2024-05-03 04:53:43", - "languages": [], - "model_or_dataset": "model", - "model_size": 6.83, - "model_architectures": null + "model_architectures": "BertForSequenceClassification" }, { "description": "Llama-3-8B-Japanese-Instruct-GGUF Original Model haqishen/Llama-3-8B-Japanese-Instruct Run with Gaianet Prompt template: prompt template: llama-3-chat Context size: chat_ctx_size: 4096 Run with GaiaNet:", "url": "https://huggingface.co/gaianet/Llama-3-8B-Japanese-Instruct-GGUF", "project_name": "Llama-3-8B-Japanese-Instruct-GGUF", - "downloads": 237, + "downloads": 232, "source": "Hugging Face", - "score": -0.1107223059386703, + "score": -0.09033465405182886, "first_commit": "2024-05-14 05:38:05", "latest_commit": "2024-05-16 13:44:53", "languages": [], @@ -7186,82 +7289,68 @@ "model_architectures": null }, { - "description": "old？ ", - "url": "https://huggingface.co/Lasorco/lametta_old", - "project_name": "lametta_old", - "downloads": 235, - "source": "Hugging Face", - "score": -0.11075372865205874, - "first_commit": "2023-05-21 11:16:50", - "latest_commit": "2024-07-23 07:24:33", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": null - }, - { - "description": "alfredplpl-Llama-3-8B-Instruct-Ja-gguf alfredplplさんが公開しているLlama-3-8B-Instruct-Jaのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/alfredplpl-Llama-3-8B-Instruct-Ja-gguf", - "project_name": "alfredplpl-Llama-3-8B-Instruct-Ja-gguf", - "downloads": 233, + "description": "Umievo-itr012-Gleipnir-7B-GGUF", + "url": "https://huggingface.co/QuantFactory/Umievo-itr012-Gleipnir-7B-GGUF", + "project_name": "Umievo-itr012-Gleipnir-7B-GGUF", + "downloads": 223, "source": "Hugging Face", - "score": -0.11078515136544717, - "first_commit": "2024-04-23 14:18:57", - "latest_commit": "2024-04-23 15:24:47", + "score": -0.09043009860665586, + "first_commit": "2024-06-09 03:48:10", + "latest_commit": "2024-06-09 13:12:32", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, + "model_size": 7.24, "model_architectures": null }, { - "description": "SpeechT5 (TTS task) for Japanese SpeechT5 model fine-tuned for Japanese speech synthesis (text-to-speech)", - "url": "https://huggingface.co/esnya/japanese_speecht5_tts", - "project_name": "japanese_speecht5_tts", - "downloads": 233, + "description": "Model Card for Japanese DeBERTa V2 large Model description This is a Japanese DeBERTa V2 large model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.", + "url": "https://huggingface.co/ku-nlp/deberta-v2-large-japanese", + "project_name": "deberta-v2-large-japanese", + "downloads": 222, "source": "Hugging Face", - "score": -0.11078515136544717, - "first_commit": "2023-08-08 18:37:40", - "latest_commit": "2023-08-09 09:25:38", + "score": -0.0904407035571922, + "first_commit": "2023-01-07 07:45:25", + "latest_commit": "2023-05-12 14:10:35", "languages": [], "model_or_dataset": "model", - "model_size": 0.14400000000000002, - "model_architectures": "SpeechT5ForTextToSpeech" + "model_size": 0.373, + "model_architectures": "DebertaV2ForMaskedLM" }, { - "description": "BERT small Japanese finance This is a BERT model pretrained on texts in the Japanese language.", - "url": "https://huggingface.co/izumi-lab/bert-small-japanese", - "project_name": "bert-small-japanese", - "downloads": 230, + "description": "pfnet-nekomata-14b-pfn-qfin-gguf pfnetさんが公開しているnekomata-14b-pfn-qfinのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/pfnet-nekomata-14b-pfn-qfin-gguf", + "project_name": "pfnet-nekomata-14b-pfn-qfin-gguf", + "downloads": 219, "source": "Hugging Face", - "score": -0.11083228543552982, - "first_commit": "2021-10-04 13:09:36", - "latest_commit": "2022-12-09 00:40:57", + "score": -0.0904725184088012, + "first_commit": "2024-04-24 12:58:10", + "latest_commit": "2024-04-24 14:46:15", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForMaskedLM" + "model_size": 14.2, + "model_architectures": null }, { - "description": "Model card for model ID", - "url": "https://huggingface.co/retrieva-jp/t5-large-long", - "project_name": "t5-large-long", - "downloads": 227, + "description": "QuantFactory/llama-3-youko-8b-GGUF", + "url": "https://huggingface.co/QuantFactory/llama-3-youko-8b-GGUF", + "project_name": "llama-3-youko-8b-GGUF", + "downloads": 218, "source": "Hugging Face", - "score": -0.11087941950561248, - "first_commit": "2023-04-26 08:33:12", - "latest_commit": "2023-05-10 10:00:35", + "score": -0.09048312335933753, + "first_commit": "2024-06-24 05:04:12", + "latest_commit": "2024-06-24 06:35:40", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "T5ForConditionalGeneration" + "model_architectures": null }, { "description": "Evaluation on MIRACL japanese These models don't train on the MIRACL training data.", "url": "https://huggingface.co/aken12/splade-japanese-v3", "project_name": "splade-japanese-v3", - "downloads": 225, + "downloads": 217, "source": "Hugging Face", - "score": -0.11091084221900091, + "score": -0.09049372830987387, "first_commit": "2024-03-29 12:35:47", "latest_commit": "2024-05-22 02:59:37", "languages": [], @@ -7270,96 +7359,96 @@ "model_architectures": "BertForMaskedLM" }, { - "description": "pfnet-nekomata-14b-pfn-qfin-gguf pfnetさんが公開しているnekomata-14b-pfn-qfinのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/pfnet-nekomata-14b-pfn-qfin-gguf", - "project_name": "pfnet-nekomata-14b-pfn-qfin-gguf", - "downloads": 221, + "description": "Rakuda - Questions for Japanese models Repository:", + "url": "https://huggingface.co/datasets/yuzuai/rakuda-questions", + "project_name": "rakuda-questions", + "downloads": 217, "source": "Hugging Face", - "score": -0.11097368764577778, - "first_commit": "2024-04-24 12:58:10", - "latest_commit": "2024-04-24 14:46:15", + "score": -0.09049372830987387, + "first_commit": "2023-06-23 01:08:54", + "latest_commit": "2023-06-23 08:01:35", "languages": [], - "model_or_dataset": "model", - "model_size": 14.2, + "model_or_dataset": "dataset", + "model_size": null, "model_architectures": null }, { - "description": "aya-23-8B-gguf CohereForAIさんが公開しているaya-23-8Bのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/aya-23-8B-gguf", - "project_name": "aya-23-8B-gguf", - "downloads": 218, + "description": "We provide an Amazon product reviews dataset for multilingual text classification.", + "url": "https://huggingface.co/datasets/defunct-datasets/amazon_reviews_multi", + "project_name": "amazon_reviews_multi", + "downloads": 215, "source": "Hugging Face", - "score": -0.11102082171586043, - "first_commit": "2024-05-26 16:32:53", - "latest_commit": "2024-05-27 00:54:36", + "score": -0.09051493821094654, + "first_commit": "2022-01-25 16:34:54", + "latest_commit": "2023-11-02 14:52:21", "languages": [], - "model_or_dataset": "model", - "model_size": 8.03, + "model_or_dataset": "dataset", + "model_size": null, "model_architectures": null }, { - "description": "aixsatoshi-Honyaku-13b-gguf aixsatoshiさんが公開しているHonyaku-13bのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/aixsatoshi-Honyaku-13b-gguf", - "project_name": "aixsatoshi-Honyaku-13b-gguf", - "downloads": 218, + "description": "Fugaku-LLM利用規約 この利用規約（以下「本規約」といいます）は、富士通株式会社、国立研究開発法人理化学研究所、国立大学法人東京工業大学、国立大学法人東北大学、株式会社サイバーエージェント、国立大学法人東海国立大学機構、及び株式会社Kotoba Technologies Japan (以下「開発者」といいます)による、スーパーコンピュータ「富岳」政策対応枠における大規模言語モデル分散並列学習手法の開発の成果物として公開する大規模言語モデル（以下「Fugaku-LLM」といいます）の利用に関する条件を定めるものです。", + "url": "https://huggingface.co/Fugaku-LLM/Fugaku-LLM-13B-instruct-gguf", + "project_name": "Fugaku-LLM-13B-instruct-gguf", + "downloads": 214, "source": "Hugging Face", - "score": -0.11102082171586043, - "first_commit": "2024-05-19 08:07:15", - "latest_commit": "2024-05-19 09:24:59", + "score": -0.09052554316148287, + "first_commit": null, + "latest_commit": null, "languages": [], "model_or_dataset": "model", - "model_size": 13.1, + "model_size": 13.4, "model_architectures": null }, { - "description": "Local-Novel-LLM-project様の Assistance をGGUF形式に変換したものです。 ", - "url": "https://huggingface.co/MCZK/Assistance-7B-GGUF", - "project_name": "Assistance-7B-GGUF", - "downloads": 216, + "description": "Dataset Summary This is the Business Scene Dialogue (BSD) dataset, a Japanese-English parallel corpus containing written conversations in various business scenarios.", + "url": "https://huggingface.co/datasets/ryo0634/bsd_ja_en", + "project_name": "bsd_ja_en", + "downloads": 213, "source": "Hugging Face", - "score": -0.11105224442924887, - "first_commit": "2024-05-03 12:16:29", - "latest_commit": "2024-05-04 07:48:41", + "score": -0.09053614811201921, + "first_commit": "2022-01-25 16:35:02", + "latest_commit": "2024-01-11 07:36:44", "languages": [], - "model_or_dataset": "model", - "model_size": 7.24, + "model_or_dataset": "dataset", + "model_size": null, "model_architectures": null }, { - "description": "range3/wiki40b-ja This dataset consists of three parquet files from the wiki40b dataset with only Japanese data extracted.", - "url": "https://huggingface.co/datasets/range3/wiki40b-ja", - "project_name": "wiki40b-ja", - "downloads": 216, + "description": "Mistral-7B-Instruct-v0.3-gguf mistralaiさんが公開しているMistral-7B-Instruct-v0.3のggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Mistral-7B-Instruct-v0.3-gguf", + "project_name": "Mistral-7B-Instruct-v0.3-gguf", + "downloads": 212, "source": "Hugging Face", - "score": -0.11105224442924887, - "first_commit": "2023-02-04 04:54:17", - "latest_commit": "2023-02-04 05:44:21", + "score": -0.09054675306255554, + "first_commit": "2024-05-23 14:44:25", + "latest_commit": "2024-05-23 15:58:46", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_or_dataset": "model", + "model_size": 7.25, "model_architectures": null }, { - "description": "Fugaku-LLM利用規約 この利用規約（以下「本規約」といいます）は、富士通株式会社、国立研究開発法人理化学研究所、国立大学法人東京工業大学、国立大学法人東北大学、株式会社サイバーエージェント、国立大学法人東海国立大学機構、及び株式会社Kotoba Technologies Japan (以下「開発者」といいます)による、スーパーコンピュータ「富岳」政策対応枠における大規模言語モデル分散並列学習手法の開発の成果物として公開する大規模言語モデル（以下「Fugaku-LLM」といいます）の利用に関する条件を定めるものです。", - "url": "https://huggingface.co/Fugaku-LLM/Fugaku-LLM-13B-instruct-gguf", - "project_name": "Fugaku-LLM-13B-instruct-gguf", - "downloads": 215, + "description": "ArrowPro-7B-KillerWhale-gguf DataPilotさんが公開しているArrowPro-7B-KillerWhaleのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/ArrowPro-7B-KillerWhale-gguf", + "project_name": "ArrowPro-7B-KillerWhale-gguf", + "downloads": 209, "source": "Hugging Face", - "score": -0.11106795578594308, - "first_commit": null, - "latest_commit": null, + "score": -0.09057856791416453, + "first_commit": "2024-05-29 15:06:55", + "latest_commit": "2024-05-29 15:53:17", "languages": [], "model_or_dataset": "model", - "model_size": 13.4, + "model_size": 7.24, "model_architectures": null }, { "description": "stockmark-100b-gguf stockmarkさんが公開しているstockmark-100bのggufフォーマット変換版です。 ", "url": "https://huggingface.co/mmnga/stockmark-100b-gguf", "project_name": "stockmark-100b-gguf", - "downloads": 215, + "downloads": 203, "source": "Hugging Face", - "score": -0.11106795578594308, + "score": -0.09064219761738254, "first_commit": "2024-05-17 12:45:56", "latest_commit": "2024-05-18 09:14:46", "languages": [], @@ -7367,13 +7456,27 @@ "model_size": 96.2, "model_architectures": null }, + { + "description": "日本語T5事前学習済みモデル This is a T5 (Text-to-Text Transfer Transformer) model pretrained on Japanese corpus. ", + "url": "https://huggingface.co/sonoisa/t5-base-japanese-v1.1", + "project_name": "t5-base-japanese-v1.1", + "downloads": 201, + "source": "Hugging Face", + "score": -0.09066340751845521, + "first_commit": "2022-08-12 15:41:28", + "latest_commit": "2022-08-27 09:21:01", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "T5ForConditionalGeneration" + }, { "description": "SakanaAI-EvoLLM-JP-A-v1-7B-gguf SakanaAIさんが公開しているEvoLLM-JP-A-v1-7Bのggufフォーマット変換版です。 ", "url": "https://huggingface.co/mmnga/SakanaAI-EvoLLM-JP-A-v1-7B-gguf", "project_name": "SakanaAI-EvoLLM-JP-A-v1-7B-gguf", - "downloads": 212, + "downloads": 199, "source": "Hugging Face", - "score": -0.11111508985602574, + "score": -0.09068461741952788, "first_commit": "2024-03-21 13:25:41", "latest_commit": "2024-03-21 14:48:28", "languages": [], @@ -7382,784 +7485,684 @@ "model_architectures": null }, { - "description": "ArrowPro-7B-KillerWhale-gguf DataPilotさんが公開しているArrowPro-7B-KillerWhaleのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/ArrowPro-7B-KillerWhale-gguf", - "project_name": "ArrowPro-7B-KillerWhale-gguf", - "downloads": 211, + "description": "Hibiki ASR Phonemizer This model is a Phoneme Level Speech Recognition network, originally a fine-tuned version of openai/whisper-large-v3 on a mixture of Different Japanese datasets.", + "url": "https://huggingface.co/Respair/Hibiki_ASR_Phonemizer_v0.2", + "project_name": "Hibiki_ASR_Phonemizer_v0.2", + "downloads": 196, "source": "Hugging Face", - "score": -0.11113080121271995, - "first_commit": "2024-05-29 15:06:55", - "latest_commit": "2024-05-29 15:53:17", + "score": -0.09071643227113688, + "first_commit": "2024-08-12 01:30:08", + "latest_commit": "2024-08-19 18:13:01", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, + "model_size": 1.54, + "model_architectures": "WhisperForConditionalGeneration" + }, + { + "description": "aya-23-8B-gguf CohereForAIさんが公開しているaya-23-8Bのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/aya-23-8B-gguf", + "project_name": "aya-23-8B-gguf", + "downloads": 196, + "source": "Hugging Face", + "score": -0.09071643227113688, + "first_commit": "2024-05-26 16:32:53", + "latest_commit": "2024-05-27 00:54:36", + "languages": [], + "model_or_dataset": "model", + "model_size": 8.03, "model_architectures": null }, { - "description": "Rakuda - Questions for Japanese models Repository:", - "url": "https://huggingface.co/datasets/yuzuai/rakuda-questions", - "project_name": "rakuda-questions", - "downloads": 211, + "description": "llm-japanese-dataset LLM構築用の日本語インストラクション(チャット)データセット 主に，英語で構築されたLLMモデルなどに対して，チャット(Instruction)応答タスクに関してLoRAなどでチューニングするために使用できます． ", + "url": "https://huggingface.co/datasets/izumi-lab/llm-japanese-dataset", + "project_name": "llm-japanese-dataset", + "downloads": 194, "source": "Hugging Face", - "score": -0.11113080121271995, - "first_commit": "2023-06-23 01:08:54", - "latest_commit": "2023-06-23 08:01:35", + "score": -0.09073764217220955, + "first_commit": "2023-04-30 06:13:24", + "latest_commit": "2024-01-18 13:42:50", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "What’s this?", - "url": "https://huggingface.co/globis-university/deberta-v3-japanese-base", - "project_name": "deberta-v3-japanese-base", - "downloads": 210, + "description": "Ninja-v1-RP-expressive-GGUF 概要 Aratako/Ninja-v1-RP-expressive-v2の量子化済みGGUF版です。", + "url": "https://huggingface.co/Aratako/Ninja-v1-RP-expressive-v2-GGUF", + "project_name": "Ninja-v1-RP-expressive-v2-GGUF", + "downloads": 193, "source": "Hugging Face", - "score": -0.11114651256941417, - "first_commit": "2023-09-21 16:19:31", - "latest_commit": "2024-07-05 05:49:13", + "score": -0.09074824712274589, + "first_commit": "2024-05-26 06:09:57", + "latest_commit": "2024-05-26 15:22:01", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "DebertaV2ForTokenClassification" + "model_size": 7.24, + "model_architectures": null }, { - "description": "I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information japanese-stablelm-3b-4e1t-base - GGUF Model creator: stabilityai Original model: japanese-stablelm-3b-4e1t-base StableLM", - "url": "https://huggingface.co/maddes8cht/stabilityai-japanese-stablelm-3b-4e1t-base-gguf", - "project_name": "stabilityai-japanese-stablelm-3b-4e1t-base-gguf", - "downloads": 207, + "description": "SakanaAI-EvoLLM-JP-v1-7B-gguf SakanaAIさんが公開しているEvoLLM-JP-v1-7Bのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/SakanaAI-EvoLLM-JP-v1-7B-gguf", + "project_name": "SakanaAI-EvoLLM-JP-v1-7B-gguf", + "downloads": 192, "source": "Hugging Face", - "score": -0.11119364663949682, - "first_commit": "2023-11-16 10:23:21", - "latest_commit": "2023-11-16 11:18:48", + "score": -0.09075885207328221, + "first_commit": "2024-03-21 13:04:25", + "latest_commit": "2024-03-21 14:41:04", "languages": [], "model_or_dataset": "model", - "model_size": 2.8, + "model_size": 7.24, "model_architectures": null }, { - "description": "モデル説明 (model explanation) CoolJapanDiffusion 2.1.1とWaifuDiffusion 1.4 anime epoch2のマージ。", - "url": "https://huggingface.co/ThePioneer/CoolerWaifuDiffusion", - "project_name": "CoolerWaifuDiffusion", - "downloads": 206, + "description": "Chatbot Arena Conversationsの質問文から、aixsatoshi/Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct-v2を使用して応答文を作成しました 質問文は、以下のモデルのPrompt部分を使用しました Chatbot Arena Conversations JA (calm2) 以下引用です。 ", + "url": "https://huggingface.co/datasets/aixsatoshi/Swallow-MX-chatbot-DPO", + "project_name": "Swallow-MX-chatbot-DPO", + "downloads": 192, "source": "Hugging Face", - "score": -0.11120935799619104, - "first_commit": "2023-01-20 23:52:39", - "latest_commit": "2023-01-22 19:16:59", + "score": -0.09075885207328221, + "first_commit": "2024-03-31 06:42:39", + "latest_commit": "2024-03-31 08:16:43", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "DeBERTa V2 base Japanese This is a DeBERTaV2 model pretrained on Japanese texts.", - "url": "https://huggingface.co/izumi-lab/deberta-v2-base-japanese", - "project_name": "deberta-v2-base-japanese", - "downloads": 206, + "description": "range3/wiki40b-ja This dataset consists of three parquet files from the wiki40b dataset with only Japanese data extracted.", + "url": "https://huggingface.co/datasets/range3/wiki40b-ja", + "project_name": "wiki40b-ja", + "downloads": 191, "source": "Hugging Face", - "score": -0.11120935799619104, - "first_commit": "2023-10-21 13:24:11", - "latest_commit": "2024-07-19 03:07:57", + "score": -0.09076945702381854, + "first_commit": "2023-02-04 04:54:17", + "latest_commit": "2023-02-04 05:44:21", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "DebertaV2ForMaskedLM" + "model_architectures": null }, { - "description": "Places in japan.", - "url": "https://huggingface.co/datasets/JapanDegitalMaterial/Places_in_Japan", - "project_name": "Places_in_Japan", - "downloads": 203, + "description": "QuantFactory/Llama3.1-ArrowSE-v0.4-GGUF This is quantized version of DataPilot/Llama3.1-ArrowSE-v0.4 created using llama.cpp Original Model Card 概要 このモデルはllama3.1-8B-instructをもとに日本語性能を高めることを目的にMergekit&ファインチューニングを用いて作成されました。 ", + "url": "https://huggingface.co/QuantFactory/Llama3.1-ArrowSE-v0.4-GGUF", + "project_name": "Llama3.1-ArrowSE-v0.4-GGUF", + "downloads": 190, "source": "Hugging Face", - "score": -0.1112564920662737, - "first_commit": "2023-09-23 12:35:06", - "latest_commit": "2023-09-23 14:00:16", + "score": -0.09078006197435488, + "first_commit": "2024-07-28 06:17:48", + "latest_commit": "2024-07-28 06:57:40", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_or_dataset": "model", + "model_size": 8.03, "model_architectures": null }, { - "description": "このモデルはdeberta-v2-base-japaneseをファインチューニングしてQAタスクに用いれるようにしたものです。 ", - "url": "https://huggingface.co/Mizuiro-sakura/deberta-v2-base-japanese-finetuned-QAe", - "project_name": "deberta-v2-base-japanese-finetuned-QAe", - "downloads": 201, + "description": "Llama3ベースの日本語医療LLM MedLlama3-JP このモデルはLlama3の継続学習により作成された４種類のLLMから成るマージモデルです。 ", + "url": "https://huggingface.co/EQUES/MedLLama3-JP-v2", + "project_name": "MedLLama3-JP-v2", + "downloads": 189, "source": "Hugging Face", - "score": -0.11128791477966211, - "first_commit": "2023-01-09 11:59:13", - "latest_commit": "2023-03-27 02:43:35", + "score": -0.09079066692489121, + "first_commit": "2024-07-01 13:42:17", + "latest_commit": "2024-07-13 06:12:43", "languages": [], "model_or_dataset": "model", - "model_size": 0.112, - "model_architectures": "DebertaV2ForQuestionAnswering" + "model_size": 8.03, + "model_architectures": "LlamaForCausalLM" }, { - "description": "rinna-llama-3-youko-70b-instruct-gguf rinnaさんが公開しているllama-3-youko-70b-instructのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/rinna-llama-3-youko-70b-instruct-gguf", - "project_name": "rinna-llama-3-youko-70b-instruct-gguf", - "downloads": 199, + "description": "By clicking \"Agree\", you agree to the License Agreement and acknowledge Stability AI's Privacy Policy.", + "url": "https://huggingface.co/stabilityai/japanese-stablelm-2-base-1_6b", + "project_name": "japanese-stablelm-2-base-1_6b", + "downloads": 189, "source": "Hugging Face", - "score": -0.11131933749305055, - "first_commit": "2024-07-27 09:04:09", - "latest_commit": "2024-07-31 14:35:52", + "score": -0.09079066692489121, + "first_commit": null, + "latest_commit": null, "languages": [], "model_or_dataset": "model", - "model_size": 70.6, + "model_size": 1.64, "model_architectures": null }, { - "description": "Mistral-7B-Instruct-v0.3-gguf mistralaiさんが公開しているMistral-7B-Instruct-v0.3のggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Mistral-7B-Instruct-v0.3-gguf", - "project_name": "Mistral-7B-Instruct-v0.3-gguf", - "downloads": 198, + "description": "aixsatoshi-Honyaku-13b-gguf aixsatoshiさんが公開しているHonyaku-13bのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/aixsatoshi-Honyaku-13b-gguf", + "project_name": "aixsatoshi-Honyaku-13b-gguf", + "downloads": 188, "source": "Hugging Face", - "score": -0.11133504884974477, - "first_commit": "2024-05-23 14:44:25", - "latest_commit": "2024-05-23 15:58:46", + "score": -0.09080127187542755, + "first_commit": "2024-05-19 08:07:15", + "latest_commit": "2024-05-19 09:24:59", "languages": [], "model_or_dataset": "model", - "model_size": 7.25, + "model_size": 13.1, "model_architectures": null }, { - "description": "Sakura_dataset 商用利用可能な超小規模高品質日本語データセット。 ", - "url": "https://huggingface.co/datasets/saldra/sakura_japanese_dataset", - "project_name": "sakura_japanese_dataset", - "downloads": 198, + "description": "pfnet-Llama3-Preferred-MedSwallow-70B-gguf pfnetさんが公開しているLlama3-Preferred-MedSwallow-70Bのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/pfnet-Llama3-Preferred-MedSwallow-70B-gguf", + "project_name": "pfnet-Llama3-Preferred-MedSwallow-70B-gguf", + "downloads": 188, "source": "Hugging Face", - "score": -0.11133504884974477, - "first_commit": "2023-06-07 05:44:23", - "latest_commit": "2023-06-08 11:31:06", + "score": -0.09080127187542755, + "first_commit": "2024-07-18 15:45:16", + "latest_commit": "2024-07-19 09:14:38", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_or_dataset": "model", + "model_size": 70.6, "model_architectures": null }, { - "description": "SakanaAI-EvoLLM-JP-v1-7B-gguf SakanaAIさんが公開しているEvoLLM-JP-v1-7Bのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/SakanaAI-EvoLLM-JP-v1-7B-gguf", - "project_name": "SakanaAI-EvoLLM-JP-v1-7B-gguf", - "downloads": 197, + "description": "rinna-llama-3-youko-70b-instruct-gguf rinnaさんが公開しているllama-3-youko-70b-instructのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/rinna-llama-3-youko-70b-instruct-gguf", + "project_name": "rinna-llama-3-youko-70b-instruct-gguf", + "downloads": 188, "source": "Hugging Face", - "score": -0.11135076020643898, - "first_commit": "2024-03-21 13:04:25", - "latest_commit": "2024-03-21 14:41:04", + "score": -0.09080127187542755, + "first_commit": "2024-07-27 09:04:09", + "latest_commit": "2024-07-31 14:35:52", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, + "model_size": 70.6, "model_architectures": null }, { - "description": "Additional pretrained BERT base Japanese finance This is a BERT model pretrained on texts in the Japanese language.", - "url": "https://huggingface.co/izumi-lab/bert-base-japanese-fin-additional", - "project_name": "bert-base-japanese-fin-additional", - "downloads": 193, + "description": "Orion-14B 🌐English | 🇨", + "url": "https://huggingface.co/OrionStarAI/Orion-14B-Chat-RAG", + "project_name": "Orion-14B-Chat-RAG", + "downloads": 185, "source": "Hugging Face", - "score": -0.11141360563321585, - "first_commit": "2022-03-11 17:41:11", - "latest_commit": "2022-12-09 00:40:25", + "score": -0.09083308672703655, + "first_commit": "2024-01-16 12:19:08", + "latest_commit": "2024-03-26 10:08:09", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "BertForPreTraining" + "model_architectures": "OrionForCausalLM" }, { - "description": "Hibiki ASR Phonemizer This model is a Phoneme Level Speech Recognition network, originally a fine-tuned version of openai/whisper-large-v3 on a mixture of Different Japanese datasets.", - "url": "https://huggingface.co/Respair/Hibiki_ASR_Phonemizer_v0.2", - "project_name": "Hibiki_ASR_Phonemizer_v0.2", - "downloads": 193, + "description": "AutoWikiQA 東工大が公開しているSwallow-MXを用いて、Wikipedia中のテキストを入力として「質問(query)」と「回答(answer)」を生成し、生成された質問と回答についてフィルタリングを行ったデータセットです。", + "url": "https://huggingface.co/datasets/cl-nagoya/auto-wiki-qa", + "project_name": "auto-wiki-qa", + "downloads": 185, "source": "Hugging Face", - "score": -0.11141360563321585, - "first_commit": "2024-08-12 01:30:08", - "latest_commit": "2024-08-19 18:13:01", + "score": -0.09083308672703655, + "first_commit": "2024-03-28 01:33:42", + "latest_commit": "2024-04-20 12:17:33", "languages": [], - "model_or_dataset": "model", - "model_size": 1.54, - "model_architectures": "WhisperForConditionalGeneration" + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null }, { - "description": "Llama3ベースの日本語医療LLM MedLlama3-JP このモデルはLlama3の継続学習により作成された４種類のLLMから成るマージモデルです。 ", - "url": "https://huggingface.co/EQUES/MedLLama3-JP-v2", - "project_name": "MedLLama3-JP-v2", - "downloads": 192, + "description": "[EZO model card]", + "url": "https://huggingface.co/AXCXEPT/EZO-InternVL2-26B", + "project_name": "EZO-InternVL2-26B", + "downloads": 183, "source": "Hugging Face", - "score": -0.11142931698991007, - "first_commit": "2024-07-01 13:42:17", - "latest_commit": "2024-07-13 06:12:43", + "score": -0.09085429662810922, + "first_commit": "2024-08-19 08:03:55", + "latest_commit": "2024-08-23 10:56:47", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": "LlamaForCausalLM" + "model_size": 25.5, + "model_architectures": "InternVLChatModel" }, { - "description": "Qwen1.5-110B-Chat-gguf Qwenさんが公開しているQwen1.5-110B-Chatのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Qwen1.5-110B-Chat-gguf", - "project_name": "Qwen1.5-110B-Chat-gguf", - "downloads": 190, + "description": "Japanese-WizardLM2-ChatV-7B-GGUF GGUF conversion of \"Japanese-WizardLM2-ChatV-7B\" This model, Japanese-WizardLM2-ChatV-7B, is based on \"chatntq-ja-7b-v1.0 \", and was created by subtracting \"Mistral-7B-v0.1\" from \"WizardLM-2-7b\" ChatVector was added by a factor of 1.0.", + "url": "https://huggingface.co/umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF", + "project_name": "Japanese-WizardLM2-ChatV-7B-GGUF", + "downloads": 179, "source": "Hugging Face", - "score": -0.1114607397032985, - "first_commit": "2024-04-27 19:35:48", - "latest_commit": "2024-04-28 08:09:17", + "score": -0.09089671643025456, + "first_commit": "2024-04-16 14:45:30", + "latest_commit": "2024-04-17 01:41:16", "languages": [], "model_or_dataset": "model", - "model_size": 111.0, + "model_size": 7.24, "model_architectures": null }, { - "description": "ELYZA-japanese-CodeLlama-7b-gguf ELYZAさんが公開しているELYZA-japanese-CodeLlama-7b-instructのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/ELYZA-japanese-CodeLlama-7b-gguf", - "project_name": "ELYZA-japanese-CodeLlama-7b-gguf", - "downloads": 190, + "description": "HODACHI様の Llama-3.1-8B-EZO-1.1-it をGGUF形式に変換したものです。 ", + "url": "https://huggingface.co/MCZK/Llama-3.1-8B-EZO-1.1-it-GGUF", + "project_name": "Llama-3.1-8B-EZO-1.1-it-GGUF", + "downloads": 176, "source": "Hugging Face", - "score": -0.1114607397032985, - "first_commit": "2023-11-15 09:53:42", - "latest_commit": "2023-11-16 14:28:03", + "score": -0.09092853128186355, + "first_commit": "2024-07-31 12:12:01", + "latest_commit": "2024-07-31 18:13:59", "languages": [], "model_or_dataset": "model", - "model_size": 6.74, + "model_size": 8.03, "model_architectures": null }, { - "description": "Wav2Vec2-Large-XLSR-53-Japanese Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using the Common Voice and Japanese speech corpus of Saruwatari-lab, University of Tokyo JSUT.", - "url": "https://huggingface.co/vumichien/wav2vec2-large-xlsr-japanese-hiragana", - "project_name": "wav2vec2-large-xlsr-japanese-hiragana", - "downloads": 182, + "description": "Fugaku-LLM利用規約 この利用規約（以下「本規約」といいます）は、富士通株式会社、国立研究開発法人理化学研究所、国立大学法人東京工業大学、国立大学法人東北大学、株式会社サイバーエージェント、国立大学法人東海国立大学機構、及び株式会社Kotoba Technologies Japan (以下「開発者」といいます)による、スーパーコンピュータ「富岳」政策対応枠における大規模言語モデル分散並列学習手法の開発の成果物として公開する大規模言語モデル（以下「Fugaku-LLM」といいます）の利用に関する条件を定めるものです。", + "url": "https://huggingface.co/Fugaku-LLM/Fugaku-LLM-13B", + "project_name": "Fugaku-LLM-13B", + "downloads": 174, "source": "Hugging Face", - "score": -0.11158643055685225, - "first_commit": "2021-06-18 07:15:24", - "latest_commit": "2023-02-08 00:36:47", + "score": -0.09094974118293622, + "first_commit": null, + "latest_commit": null, "languages": [], "model_or_dataset": "model", - "model_size": 0.316, - "model_architectures": "Wav2Vec2ForCTC" + "model_size": null, + "model_architectures": null }, { - "description": "By clicking \"Agree\", you agree to the License Agreement and acknowledge Stability AI's Privacy Policy.", - "url": "https://huggingface.co/stabilityai/japanese-stablelm-2-base-1_6b", - "project_name": "japanese-stablelm-2-base-1_6b", - "downloads": 182, - "source": "Hugging Face", - "score": -0.11158643055685225, - "first_commit": null, - "latest_commit": null, - "languages": [], - "model_or_dataset": "model", - "model_size": 1.64, - "model_architectures": null - }, - { - "description": "Japanese Morphological Analysis written in Rust", - "url": "https://github.com/Leko/goya", - "project_name": "goya", - "stargazers_count": 77, - "source": "GitHub", - "score": -0.11160936093713796, - "first_commit": "2021-09-08 19:51:11", - "latest_commit": "2021-12-30 19:44:15", - "languages": [ - "Rust", - "JavaScript", - "TypeScript" - ], - "model_or_dataset": null - }, - { - "description": "Japanese tokenizer for Transformers", - "url": "https://github.com/WorksApplications/SudachiTra", - "project_name": "SudachiTra", - "stargazers_count": 77, - "source": "GitHub", - "score": -0.11160936093713796, - "first_commit": "2021-06-22 19:48:29", - "latest_commit": "2023-12-15 08:13:45", - "languages": [ - "Python" - ], - "model_or_dataset": "model" - }, - { - "description": "UNICODE絵文字の日本語読み/キーワード/分類辞書", - "url": "https://github.com/yagays/emoji-ja", - "project_name": "emoji-ja", - "stargazers_count": 77, - "source": "GitHub", - "score": -0.11160936093713796, - "first_commit": "2018-08-24 08:25:08", - "latest_commit": "2023-05-09 14:57:44", - "languages": [ - "Python" - ], - "model_or_dataset": "dataset" - }, - { - "description": "Stanza model for Japanese (ja)", - "url": "https://huggingface.co/stanfordnlp/stanza-ja", - "project_name": "stanza-ja", - "downloads": 180, + "description": "Manga OCR Optical character recognition for Japanese text, with the main focus being Japanese manga.", + "url": "https://huggingface.co/TeamFnord/manga-ocr", + "project_name": "manga-ocr", + "downloads": 174, "source": "Hugging Face", - "score": -0.11161785327024068, - "first_commit": "2021-09-07 12:05:41", - "latest_commit": "2024-07-31 05:09:43", + "score": -0.09094974118293622, + "first_commit": "2022-01-15 17:39:06", + "latest_commit": "2022-02-10 07:50:15", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "VisionEncoderDecoderModel" }, { - "description": "Chat & support: TheBloke's Discord server Want to contribute?", - "url": "https://huggingface.co/TheBloke/japanese-stablelm-base-beta-70B-GGUF", - "project_name": "japanese-stablelm-base-beta-70B-GGUF", - "downloads": 177, + "description": "Japanese E5 Mixtral 7B Slerp GGUF GGUF conversion of oshizo/japanese-e5-mistral-7b_slerp Avaiable formats: Q2_K.gguf Q3_K.gguf Q4_K.gguf Q5_K.gguf", + "url": "https://huggingface.co/mm/japanese-e5-mistral-7b_slerp_gguf", + "project_name": "japanese-e5-mistral-7b_slerp_gguf", + "downloads": 171, "source": "Hugging Face", - "score": -0.11166498734032333, - "first_commit": "2023-11-06 11:33:47", - "latest_commit": "2023-11-06 12:14:36", + "score": -0.09098155603454523, + "first_commit": "2024-06-09 08:34:37", + "latest_commit": "2024-06-14 16:12:17", "languages": [], "model_or_dataset": "model", - "model_size": 69.0, + "model_size": 7.24, "model_architectures": null }, { - "description": "Ninja-v1-RP-expressive-GGUF 概要 Aratako/Ninja-v1-RP-expressiveの量子化済みGGUF版です。", - "url": "https://huggingface.co/Aratako/Ninja-v1-RP-expressive-GGUF", - "project_name": "Ninja-v1-RP-expressive-GGUF", - "downloads": 175, + "description": "ryota39様の Tora-7B-v0.1 をGGUF形式に変換したものです。 ", + "url": "https://huggingface.co/MCZK/Tora-7B-v0.1-GGUF", + "project_name": "Tora-7B-v0.1-GGUF", + "downloads": 171, "source": "Hugging Face", - "score": -0.11169641005371177, - "first_commit": "2024-05-21 12:16:42", - "latest_commit": "2024-05-24 15:11:25", + "score": -0.09098155603454523, + "first_commit": "2024-05-07 11:24:35", + "latest_commit": "2024-06-15 03:16:21", "languages": [], "model_or_dataset": "model", "model_size": 7.24, "model_architectures": null }, { - "description": "By clicking \"Agree\", you agree to the License Agreement and acknowledge Stability AI's Privacy Policy.", - "url": "https://huggingface.co/stabilityai/japanese-stable-vlm", - "project_name": "japanese-stable-vlm", - "downloads": 175, + "description": "GPT-2 small Japanese model This repository contains a GPT2-small model trained on Japanese Wikipedia dataset.", + "url": "https://huggingface.co/colorfulscoop/gpt2-small-ja", + "project_name": "gpt2-small-ja", + "downloads": 171, "source": "Hugging Face", - "score": -0.11169641005371177, - "first_commit": null, - "latest_commit": null, + "score": -0.09098155603454523, + "first_commit": "2021-03-27 02:27:05", + "latest_commit": "2021-09-27 20:50:17", "languages": [], "model_or_dataset": "model", - "model_size": 7.57, - "model_architectures": null + "model_size": null, + "model_architectures": "GPT2LMHeadModel" }, { - "description": "Japanese Anime Speech Dataset 日本語はこちら japanese-anime-speech is an audio-text dataset designed for the training of automatic speech recognition models.", - "url": "https://huggingface.co/datasets/joujiboi/japanese-anime-speech", - "project_name": "japanese-anime-speech", - "downloads": 175, + "description": "読み込み方 from datasets import load_dataset dataset = load_dataset(\"YANS-official/ogiri-bokete\", split=\"train\") 概要 大喜利投稿サイトBoketeのクロールデータです。", + "url": "https://huggingface.co/datasets/YANS-official/ogiri-bokete", + "project_name": "ogiri-bokete", + "downloads": 170, "source": "Hugging Face", - "score": -0.11169641005371177, - "first_commit": "2023-11-07 13:53:40", - "latest_commit": "2024-06-30 10:06:34", + "score": -0.09099216098508156, + "first_commit": "2024-07-21 09:58:15", + "latest_commit": "2024-08-31 09:24:55", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "Umievo-itr012-Gleipnir-7B-GGUF", - "url": "https://huggingface.co/QuantFactory/Umievo-itr012-Gleipnir-7B-GGUF", - "project_name": "Umievo-itr012-Gleipnir-7B-GGUF", - "downloads": 174, + "description": "Ninja-v1-RP-expressive-GGUF 概要 Aratako/Oumuamua-7b-RPの量子化済みGGUF版です。", + "url": "https://huggingface.co/Aratako/Oumuamua-7b-RP-GGUF", + "project_name": "Oumuamua-7b-RP-GGUF", + "downloads": 168, "source": "Hugging Face", - "score": -0.11171212141040598, - "first_commit": "2024-06-09 03:48:10", - "latest_commit": "2024-06-09 13:12:32", + "score": -0.09101337088615423, + "first_commit": "2024-06-23 13:00:02", + "latest_commit": "2024-06-23 14:45:14", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, + "model_size": 7.33, "model_architectures": null }, { - "description": "Model Card for Tanrei/GPTSAN-japanese General-purpose Swich transformer based Japanese language model GPTSAN has some unique features.", - "url": "https://huggingface.co/Tanrei/GPTSAN-japanese", - "project_name": "GPTSAN-japanese", - "downloads": 174, + "description": "Fugaku-LLM利用規約 この利用規約（以下「本規約」といいます）は、富士通株式会社、国立研究開発法人理化学研究所、国立大学法人東京工業大学、国立大学法人東北大学、株式会社サイバーエージェント、国立大学法人東海国立大学機構、及び株式会社Kotoba Technologies Japan (以下「開発者」といいます)による、スーパーコンピュータ「富岳」政策対応枠における大規模言語モデル分散並列学習手法の開発の成果物として公開する大規模言語モデル（以下「Fugaku-LLM」といいます）の利用に関する条件を定めるものです。", + "url": "https://huggingface.co/Fugaku-LLM/Fugaku-LLM-13B-instruct", + "project_name": "Fugaku-LLM-13B-instruct", + "downloads": 168, "source": "Hugging Face", - "score": -0.11171212141040598, - "first_commit": "2023-01-06 05:41:12", - "latest_commit": "2023-04-21 19:04:49", + "score": -0.09101337088615423, + "first_commit": null, + "latest_commit": null, "languages": [], "model_or_dataset": "model", - "model_size": 2.78, - "model_architectures": "GPTSanJapaneseForConditionalGeneration" + "model_size": 13.2, + "model_architectures": null }, { - "description": "Our Models Vecteus Ninja-v1 Ninja-v1-NSFW Ninja-v1-128k Ninja-v1-NSFW-128k Model Card for VecTeus-v1.0 The Mistral-7B--based Large Language Model (LLM) is an noveldataset fine-tuned version of the Mistral-7B-v0.1 VecTeus has the following changes compared to Mistral-7B-v0.1.", - "url": "https://huggingface.co/Local-Novel-LLM-project/Vecteus-v1", - "project_name": "Vecteus-v1", - "downloads": 171, + "description": "By clicking \"Agree\", you agree to the License Agreement and acknowledge Stability AI's Privacy Policy.", + "url": "https://huggingface.co/stabilityai/japanese-stable-clip-vit-l-16", + "project_name": "japanese-stable-clip-vit-l-16", + "downloads": 165, "source": "Hugging Face", - "score": -0.11175925548048864, - "first_commit": "2024-05-01 02:08:01", - "latest_commit": "2024-05-04 04:07:22", + "score": -0.09104518573776323, + "first_commit": null, + "latest_commit": null, "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": "MistralForCausalLM" + "model_size": 0.41400000000000003, + "model_architectures": null }, { - "description": "Fugaku-LLM利用規約 この利用規約（以下「本規約」といいます）は、富士通株式会社、国立研究開発法人理化学研究所、国立大学法人東京工業大学、国立大学法人東北大学、株式会社サイバーエージェント、国立大学法人東海国立大学機構、及び株式会社Kotoba Technologies Japan (以下「開発者」といいます)による、スーパーコンピュータ「富岳」政策対応枠における大規模言語モデル分散並列学習手法の開発の成果物として公開する大規模言語モデル（以下「Fugaku-LLM」といいます）の利用に関する条件を定めるものです。", - "url": "https://huggingface.co/Fugaku-LLM/Fugaku-LLM-13B", - "project_name": "Fugaku-LLM-13B", - "downloads": 170, + "description": "DataPilot様の ArrowPro-7B-KUJIRA をGGUF形式に変換したものです。 ", + "url": "https://huggingface.co/MCZK/ArrowPro-7B-KUJIRA-GGUF", + "project_name": "ArrowPro-7B-KUJIRA-GGUF", + "downloads": 162, "source": "Hugging Face", - "score": -0.11177496683718285, - "first_commit": null, - "latest_commit": null, + "score": -0.09107700058937224, + "first_commit": "2024-05-09 13:34:05", + "latest_commit": "2024-05-09 23:32:52", "languages": [], "model_or_dataset": "model", - "model_size": null, + "model_size": 7.24, "model_architectures": null }, { - "description": "Japanese-WizardLM2-ChatV-7B-GGUF GGUF conversion of \"Japanese-WizardLM2-ChatV-7B\" This model, Japanese-WizardLM2-ChatV-7B, is based on \"chatntq-ja-7b-v1.0 \", and was created by subtracting \"Mistral-7B-v0.1\" from \"WizardLM-2-7b\" ChatVector was added by a factor of 1.0.", - "url": "https://huggingface.co/umiyuki/Japanese-WizardLM2-ChatV-7B-GGUF", - "project_name": "Japanese-WizardLM2-ChatV-7B-GGUF", - "downloads": 169, + "description": "Wav2Vec2-Large-XLSR-53-Japanese Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using the Common Voice and Japanese speech corpus of Saruwatari-lab, University of Tokyo JSUT.", + "url": "https://huggingface.co/vumichien/wav2vec2-large-xlsr-japanese-hiragana", + "project_name": "wav2vec2-large-xlsr-japanese-hiragana", + "downloads": 161, "source": "Hugging Face", - "score": -0.11179067819387707, - "first_commit": "2024-04-16 14:45:30", - "latest_commit": "2024-04-17 01:41:16", + "score": -0.09108760553990856, + "first_commit": "2021-06-18 07:15:24", + "latest_commit": "2023-02-08 00:36:47", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": null + "model_size": 0.316, + "model_architectures": "Wav2Vec2ForCTC" }, { - "description": "Manga OCR Optical character recognition for Japanese text, with the main focus being Japanese manga.", - "url": "https://huggingface.co/TeamFnord/manga-ocr", - "project_name": "manga-ocr", - "downloads": 168, + "description": "Oumuamua-7b-instruct-GGUF This is quantized version of nitky/Oumuamua-7b-instruct created using llama.cpp Model Description This is a merge of pre-trained language models created using mergekit. ", + "url": "https://huggingface.co/QuantFactory/Oumuamua-7b-instruct-GGUF", + "project_name": "Oumuamua-7b-instruct-GGUF", + "downloads": 159, "source": "Hugging Face", - "score": -0.11180638955057129, - "first_commit": "2022-01-15 17:39:06", - "latest_commit": "2022-02-10 07:50:15", + "score": -0.09110881544098123, + "first_commit": "2024-06-19 08:52:12", + "latest_commit": "2024-06-19 11:40:58", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "VisionEncoderDecoderModel" + "model_size": 7.33, + "model_architectures": null }, { - "description": "QuantFactory/llama-3-youko-8b-GGUF", - "url": "https://huggingface.co/QuantFactory/llama-3-youko-8b-GGUF", - "project_name": "llama-3-youko-8b-GGUF", - "downloads": 166, + "description": "Stanza model for Japanese (ja)", + "url": "https://huggingface.co/stanfordnlp/stanza-ja", + "project_name": "stanza-ja", + "downloads": 157, "source": "Hugging Face", - "score": -0.11183781226395972, - "first_commit": "2024-06-24 05:04:12", - "latest_commit": "2024-06-24 06:35:40", + "score": -0.0911300253420539, + "first_commit": "2021-09-07 12:05:41", + "latest_commit": "2024-07-31 05:09:43", "languages": [], "model_or_dataset": "model", "model_size": null, "model_architectures": null }, { - "description": "Ninja-v1-RP-expressive-GGUF 概要 Aratako/Oumuamua-7b-RPの量子化済みGGUF版です。", - "url": "https://huggingface.co/Aratako/Oumuamua-7b-RP-GGUF", - "project_name": "Oumuamua-7b-RP-GGUF", - "downloads": 165, + "description": "GitHub リポジトリ singletongue/wikipedia-utils で公開されているデータセットを利用しています。 ", + "url": "https://huggingface.co/datasets/llm-book/jawiki-sentences", + "project_name": "jawiki-sentences", + "downloads": 157, "source": "Hugging Face", - "score": -0.11185352362065394, - "first_commit": "2024-06-23 13:00:02", - "latest_commit": "2024-06-23 14:45:14", + "score": -0.0911300253420539, + "first_commit": "2023-06-03 03:02:08", + "latest_commit": "2023-10-25 15:22:05", "languages": [], - "model_or_dataset": "model", - "model_size": 7.33, + "model_or_dataset": "dataset", + "model_size": null, "model_architectures": null }, { - "description": "Tanuki-8B-dpo-v1.0-GGUF 概要 GENIAC 松尾研 LLM開発プロジェクトで開発されたLLMであるweblab-GENIAC/Tanuki-8B-dpo-v1.0-4kのGGUF量子化モデルです。", - "url": "https://huggingface.co/team-hatakeyama-phase2/Tanuki-8B-dpo-v1.0-4k-GGUF", - "project_name": "Tanuki-8B-dpo-v1.0-4k-GGUF", - "downloads": 163, + "description": "Chat & support: TheBloke's Discord server Want to contribute?", + "url": "https://huggingface.co/TheBloke/japanese-stablelm-base-beta-70B-GGUF", + "project_name": "japanese-stablelm-base-beta-70B-GGUF", + "downloads": 156, "source": "Hugging Face", - "score": -0.11188494633404238, - "first_commit": "2024-08-16 12:39:31", - "latest_commit": "2024-08-27 18:05:25", + "score": -0.09114063029259023, + "first_commit": "2023-11-06 11:33:47", + "latest_commit": "2023-11-06 12:14:36", "languages": [], "model_or_dataset": "model", - "model_size": 7.51, + "model_size": 69.0, "model_architectures": null }, { - "description": "shisa-7b-v1-gguf augmxntさんが公開しているshisa-7b-v1のggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/shisa-7b-v1-gguf", - "project_name": "shisa-7b-v1-gguf", - "downloads": 162, + "description": "c4ai-command-r-v01-japanese-instruct-GGUF 概要 Aratako/c4ai-command-r-v01-japanese-instructの量子化済みGGUF版です。", + "url": "https://huggingface.co/Aratako/c4ai-command-r-v01-japanese-instruct-GGUF", + "project_name": "c4ai-command-r-v01-japanese-instruct-GGUF", + "downloads": 155, "source": "Hugging Face", - "score": -0.1119006576907366, - "first_commit": "2023-12-09 14:02:20", - "latest_commit": "2023-12-10 12:24:25", + "score": -0.09115123524312657, + "first_commit": "2024-04-05 17:10:51", + "latest_commit": "2024-04-07 03:19:34", "languages": [], "model_or_dataset": "model", - "model_size": 7.96, + "model_size": 35.0, "model_architectures": null }, { - "description": "I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information japanese-stablelm-3b-4e1t-instruct - GGUF Model creator: stabilityai Original model: japanese-stablelm-3b-4e1t-instruct StableLM", - "url": "https://huggingface.co/maddes8cht/stabilityai-japanese-stablelm-3b-4e1t-instruct-gguf", - "project_name": "stabilityai-japanese-stablelm-3b-4e1t-instruct-gguf", - "downloads": 160, + "description": "このモデルはdeberta-v2-base-japaneseをファインチューニングしてQAタスクに用いれるようにしたものです。 ", + "url": "https://huggingface.co/Mizuiro-sakura/deberta-v2-base-japanese-finetuned-QAe", + "project_name": "deberta-v2-base-japanese-finetuned-QAe", + "downloads": 153, "source": "Hugging Face", - "score": -0.11193208040412503, - "first_commit": "2023-11-16 10:25:20", - "latest_commit": "2023-11-16 12:53:33", + "score": -0.09117244514419924, + "first_commit": "2023-01-09 11:59:13", + "latest_commit": "2023-03-27 02:43:35", "languages": [], "model_or_dataset": "model", - "model_size": 2.8, - "model_architectures": null + "model_size": 0.112, + "model_architectures": "DebertaV2ForQuestionAnswering" }, { - "description": "MobileBERT 日本語事前学習済みモデル爆誕！！ ", - "url": "https://huggingface.co/ysakuramoto/mobilebert-ja", - "project_name": "mobilebert-ja", - "downloads": 159, + "description": "By clicking \"Agree\", you agree to the License Agreement and acknowledge Stability AI's Privacy Policy.", + "url": "https://huggingface.co/stabilityai/japanese-stable-vlm", + "project_name": "japanese-stable-vlm", + "downloads": 152, "source": "Hugging Face", - "score": -0.11194779176081925, - "first_commit": "2022-01-23 11:29:39", - "latest_commit": "2022-01-24 05:25:31", + "score": -0.09118305009473557, + "first_commit": null, + "latest_commit": null, "languages": [], "model_or_dataset": "model", - "model_size": null, + "model_size": 7.57, "model_architectures": null }, { - "description": "Japanese-LLaMA-3-8B Japanese-LLaMA-3-8Bは基盤モデル、フルモデルです。 ", - "url": "https://huggingface.co/owner203/japanese-llama-3-8b", - "project_name": "japanese-llama-3-8b", - "downloads": 154, - "source": "Hugging Face", - "score": -0.11202634854429032, - "first_commit": "2024-06-05 02:19:05", - "latest_commit": "2024-06-21 06:35:41", - "languages": [], - "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": "LlamaForCausalLM" - }, - { - "description": "Kotoba-Speech-v0.1 Kotoba-Speech v0.1 is a 1.2B Transformer-based speech generative model.", - "url": "https://huggingface.co/kotoba-tech/kotoba-speech-v0.1", - "project_name": "kotoba-speech-v0.1", - "downloads": 154, + "description": "databricks-dolly-15k-ja This repository provides an instruction tuning dataset developed by LLM-jp, a collaborative project launched in Japan.", + "url": "https://huggingface.co/datasets/llm-jp/databricks-dolly-15k-ja", + "project_name": "databricks-dolly-15k-ja", + "downloads": 151, "source": "Hugging Face", - "score": -0.11202634854429032, - "first_commit": "2024-03-14 01:21:58", - "latest_commit": "2024-04-17 07:54:48", + "score": -0.09119365504527191, + "first_commit": "2024-01-27 07:11:25", + "latest_commit": "2024-01-30 18:09:37", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "GPT-2 small Japanese model This repository contains a GPT2-small model trained on Japanese Wikipedia dataset.", - "url": "https://huggingface.co/colorfulscoop/gpt2-small-ja", - "project_name": "gpt2-small-ja", - "downloads": 153, - "source": "Hugging Face", - "score": -0.11204205990098454, - "first_commit": "2021-03-27 02:27:05", - "latest_commit": "2021-09-27 20:50:17", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "GPT2LMHeadModel" - }, - { - "description": "Model Card for Japanese DeBERTa V2 large Model description This is a Japanese DeBERTa V2 large model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.", - "url": "https://huggingface.co/ku-nlp/deberta-v2-large-japanese", - "project_name": "deberta-v2-large-japanese", - "downloads": 152, - "source": "Hugging Face", - "score": -0.11205777125767875, - "first_commit": "2023-01-07 07:45:25", - "latest_commit": "2023-05-12 14:10:35", - "languages": [], - "model_or_dataset": "model", - "model_size": 0.373, - "model_architectures": "DebertaV2ForMaskedLM" - }, - { - "description": "GitHub リポジトリ singletongue/wikipedia-utils で公開されているデータセットを利用しています。 ", - "url": "https://huggingface.co/datasets/llm-book/jawiki-sentences", - "project_name": "jawiki-sentences", + "description": "oasst2-33k-ja This repository provides an instruction tuning dataset developed by LLM-jp, a collaborative project launched in Japan.", + "url": "https://huggingface.co/datasets/llm-jp/oasst2-33k-ja", + "project_name": "oasst2-33k-ja", "downloads": 151, "source": "Hugging Face", - "score": -0.11207348261437297, - "first_commit": "2023-06-03 03:02:08", - "latest_commit": "2023-10-25 15:22:05", + "score": -0.09119365504527191, + "first_commit": "2024-04-28 16:24:00", + "latest_commit": "2024-04-28 16:39:03", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "Oumuamua-7b-instruct-GGUF This is quantized version of nitky/Oumuamua-7b-instruct created using llama.cpp Model Description This is a merge of pre-trained language models created using mergekit. ", - "url": "https://huggingface.co/QuantFactory/Oumuamua-7b-instruct-GGUF", - "project_name": "Oumuamua-7b-instruct-GGUF", + "description": "概要 このモデルはllama3.1-8B-instructをもとに日本語性能を高めることを目的にMergekit&ファインチューニングを用いて作成されました。 ", + "url": "https://huggingface.co/DataPilot/Llama3.1-ArrowSE-v0.4", + "project_name": "Llama3.1-ArrowSE-v0.4", "downloads": 149, "source": "Hugging Face", - "score": -0.1121049053277614, - "first_commit": "2024-06-19 08:52:12", - "latest_commit": "2024-06-19 11:40:58", + "score": -0.09121486494634456, + "first_commit": "2024-07-24 07:37:16", + "latest_commit": "2024-07-24 12:00:46", "languages": [], "model_or_dataset": "model", - "model_size": 7.33, - "model_architectures": null + "model_size": 8.03, + "model_architectures": "LlamaForCausalLM" }, { - "description": "日本語T5 Prefix Language Model", - "url": "https://huggingface.co/sonoisa/t5-base-japanese-adapt", - "project_name": "t5-base-japanese-adapt", - "downloads": 148, + "description": "Our Models Vecteus Ninja-v1 Ninja-v1-NSFW Ninja-v1-128k Ninja-v1-NSFW-128k Model Card for VecTeus-v1.0 The Mistral-7B--based Large Language Model (LLM) is an noveldataset fine-tuned version of the Mistral-7B-v0.1 VecTeus has the following changes compared to Mistral-7B-v0.1.", + "url": "https://huggingface.co/Local-Novel-LLM-project/Vecteus-v1", + "project_name": "Vecteus-v1", + "downloads": 149, "source": "Hugging Face", - "score": -0.11212061668445562, - "first_commit": "2022-08-27 08:51:11", - "latest_commit": "2022-11-05 09:34:10", + "score": -0.09121486494634456, + "first_commit": "2024-05-01 02:08:01", + "latest_commit": "2024-05-04 04:07:22", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "T5ForConditionalGeneration" + "model_size": 7.24, + "model_architectures": "MistralForCausalLM" }, { - "description": "abc-multiple-choice Dataset abc-multiple-choice は、競技クイズの大会「abc」で使用された4択問題を元に作成された、多肢選択式の質問応答データセットです。 ", - "url": "https://huggingface.co/datasets/tohoku-nlp/abc-multiple-choice", - "project_name": "abc-multiple-choice", + "description": "Japanese Anime Speech Dataset 日本語はこちら japanese-anime-speech is an audio-text dataset designed for the training of automatic speech recognition models.", + "url": "https://huggingface.co/datasets/joujiboi/japanese-anime-speech", + "project_name": "japanese-anime-speech", "downloads": 148, "source": "Hugging Face", - "score": -0.11212061668445562, - "first_commit": "2024-03-02 03:58:25", - "latest_commit": "2024-03-12 07:32:13", + "score": -0.0912254698968809, + "first_commit": "2023-11-07 13:53:40", + "latest_commit": "2024-06-30 10:06:34", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "概要 このモデルはllama3.1-8B-instructをもとに日本語性能を高めることを目的にMergekit&ファインチューニングを用いて作成されました。 ", - "url": "https://huggingface.co/DataPilot/Llama3.1-ArrowSE-v0.4", - "project_name": "Llama3.1-ArrowSE-v0.4", - "downloads": 147, + "description": "whisper-large-v3-japanese-4k-steps This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 16.1 dataset.", + "url": "https://huggingface.co/drewschaub/whisper-large-v3-japanese-4k-steps", + "project_name": "whisper-large-v3-japanese-4k-steps", + "downloads": 146, "source": "Hugging Face", - "score": -0.11213632804114984, - "first_commit": "2024-07-24 07:37:16", - "latest_commit": "2024-07-24 12:00:46", + "score": -0.09124667979795358, + "first_commit": "2024-02-17 01:01:51", + "latest_commit": "2024-02-18 01:31:35", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": "LlamaForCausalLM" + "model_size": 1.54, + "model_architectures": "WhisperForConditionalGeneration" }, { - "description": "DataPilot様の ArrowPro-7B-KUJIRA をGGUF形式に変換したものです。 ", - "url": "https://huggingface.co/MCZK/ArrowPro-7B-KUJIRA-GGUF", - "project_name": "ArrowPro-7B-KUJIRA-GGUF", - "downloads": 147, + "description": "QuantFactory/shisa-gamma-7b-v1-GGUF", + "url": "https://huggingface.co/QuantFactory/shisa-gamma-7b-v1-GGUF", + "project_name": "shisa-gamma-7b-v1-GGUF", + "downloads": 145, "source": "Hugging Face", - "score": -0.11213632804114984, - "first_commit": "2024-05-09 13:34:05", - "latest_commit": "2024-05-09 23:32:52", + "score": -0.0912572847484899, + "first_commit": "2024-06-12 17:16:36", + "latest_commit": "2024-06-18 06:17:30", "languages": [], "model_or_dataset": "model", "model_size": 7.24, "model_architectures": null }, { - "description": "Model Trained Using AutoNLP Problem type: Binary Classification Model ID: 59362 Validation Metrics Loss: 0.13092292845249176 Accuracy: 0.9527127414314258 Precision: 0.9634070704982427 Recall: 0.9842171959602166 AUC: 0.9667289746092403 F1: 0.9737009564152002 Usage You can use cURL to access this model: $ curl -X POST -H \"Authorization: Bearer YOUR_API_KEY\" -H \"Content-Type: application/json\" -d '{\"inputs\": \"I love AutoNLP\"}' https://api-inference.huggingface.co/models/abhishek/autonlp-japanese-sentiment-5936", - "url": "https://huggingface.co/abhishek/autonlp-japanese-sentiment-59362", - "project_name": "autonlp-japanese-sentiment-59362", - "downloads": 147, - "source": "Hugging Face", - "score": -0.11213632804114984, - "first_commit": "2021-04-21 11:28:11", - "latest_commit": "2021-05-18 22:55:03", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForSequenceClassification" - }, - { - "description": "QuantFactory/Llama3-ArrowSE-8B-v0.3-GGUF This is quantized version of DataPilot/Llama3-ArrowSE-8B-v0.3 created using llama.cpp Original Model Card 概要 elyza/Llama-3-ELYZA-JP-8Bを元にchat vectorを用いて改良しAItuberに特化させました。 ", - "url": "https://huggingface.co/QuantFactory/Llama3-ArrowSE-8B-v0.3-GGUF", - "project_name": "Llama3-ArrowSE-8B-v0.3-GGUF", - "downloads": 146, + "description": "Ninja-v1-RP-expressive-GGUF 概要 Aratako/Ninja-v1-RP-expressiveの量子化済みGGUF版です。", + "url": "https://huggingface.co/Aratako/Ninja-v1-RP-expressive-GGUF", + "project_name": "Ninja-v1-RP-expressive-GGUF", + "downloads": 144, "source": "Hugging Face", - "score": -0.11215203939784406, - "first_commit": "2024-07-28 15:51:47", - "latest_commit": "2024-07-28 16:29:51", + "score": -0.09126788969902624, + "first_commit": "2024-05-21 12:16:42", + "latest_commit": "2024-05-24 15:11:25", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, + "model_size": 7.24, "model_architectures": null }, { - "description": "記事本文からタイトルを生成するモデル SEE: https://qiita.com/sonoisa/items/a9af64ff641f0bbfed44", - "url": "https://huggingface.co/sonoisa/t5-base-japanese-title-generation", - "project_name": "t5-base-japanese-title-generation", - "downloads": 146, + "description": "deberta-large-japanese-aozora Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-aozora", + "project_name": "deberta-large-japanese-aozora", + "downloads": 142, "source": "Hugging Face", - "score": -0.11215203939784406, - "first_commit": "2021-04-04 06:57:18", - "latest_commit": "2022-02-21 13:38:09", + "score": -0.09128909960009891, + "first_commit": "2022-05-26 14:46:58", + "latest_commit": "2023-01-14 00:27:22", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "T5ForConditionalGeneration" + "model_architectures": "DebertaV2ForMaskedLM" }, { - "description": "オリジナルのサイトと同じものを使用しています。 ", - "url": "https://huggingface.co/datasets/llm-book/llm-jp-eval", - "project_name": "llm-jp-eval", - "downloads": 146, + "description": "Tanuki-8x8B-dpo-v1.0-GPTQ-4bit 概要 GENIAC 松尾研 LLM開発プロジェクトで開発されたLLMであるweblab-GENIAC/Tanuki-8x8B-dpo-v1.0のGPTQ 4bit量子化モデルです。", + "url": "https://huggingface.co/team-hatakeyama-phase2/Tanuki-8x8B-dpo-v1.0-GPTQ-4bit", + "project_name": "Tanuki-8x8B-dpo-v1.0-GPTQ-4bit", + "downloads": 140, "source": "Hugging Face", - "score": -0.11215203939784406, - "first_commit": "2024-06-19 10:31:57", - "latest_commit": "2024-08-31 12:40:31", + "score": -0.09131030950117158, + "first_commit": "2024-08-27 18:19:13", + "latest_commit": "2024-09-03 09:27:14", "languages": [], - "model_or_dataset": "dataset", + "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "TanukiForCausalLM" }, { - "description": "Fugaku-LLM利用規約 この利用規約（以下「本規約」といいます）は、富士通株式会社、国立研究開発法人理化学研究所、国立大学法人東京工業大学、国立大学法人東北大学、株式会社サイバーエージェント、国立大学法人東海国立大学機構、及び株式会社Kotoba Technologies Japan (以下「開発者」といいます)による、スーパーコンピュータ「富岳」政策対応枠における大規模言語モデル分散並列学習手法の開発の成果物として公開する大規模言語モデル（以下「Fugaku-LLM」といいます）の利用に関する条件を定めるものです。", - "url": "https://huggingface.co/Fugaku-LLM/Fugaku-LLM-13B-instruct", - "project_name": "Fugaku-LLM-13B-instruct", - "downloads": 142, + "description": "SentenceTransformer based on tohoku-nlp/bert-large-japanese-v2 This is a sentence-transformers model finetuned from tohoku-nlp/bert-large-japanese-v2.", + "url": "https://huggingface.co/cl-nagoya/ruri-pt-large", + "project_name": "ruri-pt-large", + "downloads": 139, "source": "Hugging Face", - "score": -0.11221488482462093, - "first_commit": null, - "latest_commit": null, + "score": -0.09132091445170791, + "first_commit": "2024-08-19 00:58:49", + "latest_commit": "2024-08-30 00:59:26", "languages": [], "model_or_dataset": "model", - "model_size": 13.2, - "model_architectures": null + "model_size": 0.337, + "model_architectures": "BertModel" }, { - "description": "日本語T5事前学習済みモデル This is a T5 (Text-to-Text Transfer Transformer) model pretrained on Japanese corpus. ", - "url": "https://huggingface.co/sonoisa/t5-base-japanese-v1.1", - "project_name": "t5-base-japanese-v1.1", - "downloads": 141, + "description": "Japanese-Starling-ChatV-7B このモデルは\"chatntq-ja-7b-v1.0\"をベースにした7Bパラメータの日本語チャットモデルです。", + "url": "https://huggingface.co/TFMC/Japanese-Starling-ChatV-7B", + "project_name": "Japanese-Starling-ChatV-7B", + "downloads": 139, "source": "Hugging Face", - "score": -0.11223059618131515, - "first_commit": "2022-08-12 15:41:28", - "latest_commit": "2022-08-27 09:21:01", + "score": -0.09132091445170791, + "first_commit": "2024-04-14 12:18:31", + "latest_commit": "2024-04-14 15:26:06", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "T5ForConditionalGeneration" + "model_size": 7.24, + "model_architectures": "MistralForCausalLM" }, { "description": "DataPilot様の Llama3-ArrowSE-8B-v0.3 をGGUF形式に変換したものです。 ", "url": "https://huggingface.co/MCZK/Llama3-ArrowSE-8B-v0.3-GGUF", "project_name": "Llama3-ArrowSE-8B-v0.3-GGUF", - "downloads": 141, + "downloads": 139, "source": "Hugging Face", - "score": -0.11223059618131515, + "score": -0.09132091445170791, "first_commit": "2024-07-07 07:53:32", "latest_commit": "2024-07-07 13:40:26", "languages": [], @@ -8168,14 +8171,28 @@ "model_architectures": null }, { - "description": "Japanese Anime Speech Dataset V2 日本語はこちら japanese-anime-speech-v2 is an audio-text dataset designed for training automatic speech recognition models.", - "url": "https://huggingface.co/datasets/joujiboi/japanese-anime-speech-v2", - "project_name": "japanese-anime-speech-v2", - "downloads": 141, + "description": "Local-Novel-LLM-project様の Ninja-V2-7B をGGUF形式に変換したものです。 ", + "url": "https://huggingface.co/MCZK/Ninja-V2-7B-GGUF", + "project_name": "Ninja-V2-7B-GGUF", + "downloads": 139, "source": "Hugging Face", - "score": -0.11223059618131515, - "first_commit": "2024-06-26 14:18:01", - "latest_commit": "2024-07-24 19:06:51", + "score": -0.09132091445170791, + "first_commit": "2024-06-15 16:23:41", + "latest_commit": "2024-06-15 21:25:59", + "languages": [], + "model_or_dataset": "model", + "model_size": 7.24, + "model_architectures": null + }, + { + "description": "このデータセットについて このデータは、日本の官公庁のWebサイトに掲載されている「よくある質問」を手作業で抽出し、インストラクション用のデータセットとしたものです。 ", + "url": "https://huggingface.co/datasets/matsuxr/JaGovFaqs-22k", + "project_name": "JaGovFaqs-22k", + "downloads": 137, + "source": "Hugging Face", + "score": -0.09134212435278058, + "first_commit": "2023-12-31 13:58:41", + "latest_commit": "2024-02-29 02:51:20", "languages": [], "model_or_dataset": "dataset", "model_size": null, @@ -8185,9 +8202,9 @@ "description": "Model card for model ID", "url": "https://huggingface.co/retrieva-jp/t5-small-long", "project_name": "t5-small-long", - "downloads": 140, + "downloads": 135, "source": "Hugging Face", - "score": -0.11224630753800936, + "score": -0.09136333425385325, "first_commit": "2023-04-26 08:26:49", "latest_commit": "2023-05-10 10:01:29", "languages": [], @@ -8196,54 +8213,26 @@ "model_architectures": "T5ForConditionalGeneration" }, { - "description": "Deepreneur-blue-lizard-gguf Deepreneurさんが公開しているblue-lizardのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Deepreneur-blue-lizard-gguf", - "project_name": "Deepreneur-blue-lizard-gguf", - "downloads": 140, - "source": "Hugging Face", - "score": -0.11224630753800936, - "first_commit": "2024-02-13 15:18:15", - "latest_commit": "2024-02-13 16:26:26", - "languages": [], - "model_or_dataset": "model", - "model_size": 6.74, - "model_architectures": null - }, - { - "description": "Japanese-Starling-ChatV-7B このモデルは\"chatntq-ja-7b-v1.0\"をベースにした7Bパラメータの日本語チャットモデルです。", - "url": "https://huggingface.co/TFMC/Japanese-Starling-ChatV-7B", - "project_name": "Japanese-Starling-ChatV-7B", - "downloads": 140, + "description": "DataPilot様の ArrowPro-7B-RobinHood をGGUF形式に変換したものです。 ", + "url": "https://huggingface.co/MCZK/ArrowPro-7B-RobinHood-GGUF", + "project_name": "ArrowPro-7B-RobinHood-GGUF", + "downloads": 135, "source": "Hugging Face", - "score": -0.11224630753800936, - "first_commit": "2024-04-14 12:18:31", - "latest_commit": "2024-04-14 15:26:06", + "score": -0.09136333425385325, + "first_commit": "2024-05-10 12:03:26", + "latest_commit": "2024-05-10 18:14:28", "languages": [], "model_or_dataset": "model", "model_size": 7.24, - "model_architectures": "MistralForCausalLM" - }, - { - "description": "By clicking \"Agree\", you agree to the License Agreement and acknowledge Stability AI's Privacy Policy.", - "url": "https://huggingface.co/stabilityai/japanese-stable-clip-vit-l-16", - "project_name": "japanese-stable-clip-vit-l-16", - "downloads": 140, - "source": "Hugging Face", - "score": -0.11224630753800936, - "first_commit": null, - "latest_commit": null, - "languages": [], - "model_or_dataset": "model", - "model_size": 0.41400000000000003, "model_architectures": null }, { "description": "GitHub リポジトリ cl-tohoku/quiz-datasets で公開されているデータセットを利用しています。 ", "url": "https://huggingface.co/datasets/llm-book/aio-retriever", "project_name": "aio-retriever", - "downloads": 139, + "downloads": 133, "source": "Hugging Face", - "score": -0.11226201889470358, + "score": -0.09138454415492592, "first_commit": "2023-07-04 04:53:47", "latest_commit": "2023-10-25 15:31:08", "languages": [], @@ -8252,68 +8241,68 @@ "model_architectures": null }, { - "description": "ryota39様の Tora-7B-v0.1 をGGUF形式に変換したものです。 ", - "url": "https://huggingface.co/MCZK/Tora-7B-v0.1-GGUF", - "project_name": "Tora-7B-v0.1-GGUF", - "downloads": 135, + "description": "Local-Novel-LLM-project様の Vecteus-V2-7B をGGUF形式に変換したものです。 ", + "url": "https://huggingface.co/MCZK/Vecteus-V2-7B-GGUF", + "project_name": "Vecteus-V2-7B-GGUF", + "downloads": 130, "source": "Hugging Face", - "score": -0.11232486432148045, - "first_commit": "2024-05-07 11:24:35", - "latest_commit": "2024-06-15 03:16:21", + "score": -0.09141635900653491, + "first_commit": "2024-06-16 05:26:00", + "latest_commit": "2024-06-16 11:32:15", "languages": [], "model_or_dataset": "model", "model_size": 7.24, "model_architectures": null }, { - "description": "This dataset is a clarified version of the image, context, and question set included in the Japanese-Heron-Bench for the construction of the Japanese evaluation benchmark suite.", - "url": "https://huggingface.co/datasets/Silviase/Japanese-Heron-Bench", - "project_name": "Japanese-Heron-Bench", - "downloads": 132, + "description": "ryota39様の Tora-7B-v0.2 をGGUF形式に変換したものです。 ", + "url": "https://huggingface.co/MCZK/Tora-7B-v0.2-GGUF", + "project_name": "Tora-7B-v0.2-GGUF", + "downloads": 130, "source": "Hugging Face", - "score": -0.1123719983915631, - "first_commit": "2024-07-16 08:12:30", - "latest_commit": "2024-07-28 12:33:15", + "score": -0.09141635900653491, + "first_commit": "2024-05-06 12:50:49", + "latest_commit": "2024-06-15 03:17:32", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_or_dataset": "model", + "model_size": 7.24, "model_architectures": null }, { - "description": "MaziyarPanahi/japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1-GGUF Model creator: MaziyarPanahi Original model: MaziyarPanahi/japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1 Description MaziyarPanahi/japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1-GGUF contains GGUF format model files for MaziyarPanahi/japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1.", - "url": "https://huggingface.co/MaziyarPanahi/japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1-GGUF", - "project_name": "japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1-GGUF", - "downloads": 131, + "description": "Kotoba-Speech-v0.1 Kotoba-Speech v0.1 is a 1.2B Transformer-based speech generative model.", + "url": "https://huggingface.co/kotoba-tech/kotoba-speech-v0.1", + "project_name": "kotoba-speech-v0.1", + "downloads": 130, "source": "Hugging Face", - "score": -0.11238770974825732, - "first_commit": "2024-01-26 06:13:55", - "latest_commit": "2024-01-26 06:36:22", + "score": -0.09141635900653491, + "first_commit": "2024-03-14 01:21:58", + "latest_commit": "2024-04-17 07:54:48", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, + "model_size": null, "model_architectures": null }, { - "description": "llm-japanese-dataset LLM構築用の日本語インストラクション(チャット)データセット 主に，英語で構築されたLLMモデルなどに対して，チャット(Instruction)応答タスクに関してLoRAなどでチューニングするために使用できます． ", - "url": "https://huggingface.co/datasets/izumi-lab/llm-japanese-dataset", - "project_name": "llm-japanese-dataset", - "downloads": 131, + "description": "WRIME-fine-tuned BERT base Japanese This model is a Japanese BERTBASE fine-tuned on the WRIME dataset.", + "url": "https://huggingface.co/patrickramos/bert-base-japanese-v2-wrime-fine-tune", + "project_name": "bert-base-japanese-v2-wrime-fine-tune", + "downloads": 128, "source": "Hugging Face", - "score": -0.11238770974825732, - "first_commit": "2023-04-30 06:13:24", - "latest_commit": "2024-01-18 13:42:50", + "score": -0.09143756890760758, + "first_commit": "2022-05-22 09:42:14", + "latest_commit": "2023-03-22 08:11:34", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null + "model_or_dataset": "model", + "model_size": 0.111, + "model_architectures": "BertForSequenceClassification" }, { "description": "QuantFactory/shisa-7b-v1-GGUF This is quantized version of augmxnt/shisa-base-7b-v1 created using llama.cpp Model Description shisa-base-7b-v1 takes Mistral 7B and adds an additional 8B tokens of primarily Japanese pre-training.", "url": "https://huggingface.co/QuantFactory/shisa-7b-v1-GGUF", "project_name": "shisa-7b-v1-GGUF", - "downloads": 129, + "downloads": 128, "source": "Hugging Face", - "score": -0.11241913246164575, + "score": -0.09143756890760758, "first_commit": "2024-06-14 01:44:05", "latest_commit": "2024-06-18 05:53:41", "languages": [], @@ -8322,54 +8311,40 @@ "model_architectures": null }, { - "description": "Local-Novel-LLM-project様の Ninja-V2-7B をGGUF形式に変換したものです。 ", - "url": "https://huggingface.co/MCZK/Ninja-V2-7B-GGUF", - "project_name": "Ninja-V2-7B-GGUF", - "downloads": 128, + "description": "I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information japanese-stablelm-3b-4e1t-base - GGUF Model creator: stabilityai Original model: japanese-stablelm-3b-4e1t-base StableLM", + "url": "https://huggingface.co/maddes8cht/stabilityai-japanese-stablelm-3b-4e1t-base-gguf", + "project_name": "stabilityai-japanese-stablelm-3b-4e1t-base-gguf", + "downloads": 126, "source": "Hugging Face", - "score": -0.11243484381833997, - "first_commit": "2024-06-15 16:23:41", - "latest_commit": "2024-06-15 21:25:59", + "score": -0.09145877880868025, + "first_commit": "2023-11-16 10:23:21", + "latest_commit": "2023-11-16 11:18:48", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": null - }, - { - "description": "databricks-dolly-15k-ja This repository provides an instruction tuning dataset developed by LLM-jp, a collaborative project launched in Japan.", - "url": "https://huggingface.co/datasets/llm-jp/databricks-dolly-15k-ja", - "project_name": "databricks-dolly-15k-ja", - "downloads": 127, - "source": "Hugging Face", - "score": -0.11245055517503419, - "first_commit": "2024-01-27 07:11:25", - "latest_commit": "2024-01-30 18:09:37", - "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_size": 2.8, "model_architectures": null }, { - "description": "Local-Novel-LLM-project様の Vecteus-V2-7B をGGUF形式に変換したものです。 ", - "url": "https://huggingface.co/MCZK/Vecteus-V2-7B-GGUF", - "project_name": "Vecteus-V2-7B-GGUF", + "description": "MobileBERT 日本語事前学習済みモデル爆誕！！ ", + "url": "https://huggingface.co/ysakuramoto/mobilebert-ja", + "project_name": "mobilebert-ja", "downloads": 126, "source": "Hugging Face", - "score": -0.1124662665317284, - "first_commit": "2024-06-16 05:26:00", - "latest_commit": "2024-06-16 11:32:15", + "score": -0.09145877880868025, + "first_commit": "2022-01-23 11:29:39", + "latest_commit": "2022-01-24 05:25:31", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, + "model_size": null, "model_architectures": null }, { "description": "Model Card for Japanese character-level GPT-2 Medium Model description This is a Japanese character-level GPT-2 Medium (310M parameters) language model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.", "url": "https://huggingface.co/ku-nlp/gpt2-medium-japanese-char", "project_name": "gpt2-medium-japanese-char", - "downloads": 126, + "downloads": 124, "source": "Hugging Face", - "score": -0.1124662665317284, + "score": -0.09147998870975292, "first_commit": "2023-05-18 06:29:28", "latest_commit": "2023-06-08 05:34:26", "languages": [], @@ -8378,96 +8353,54 @@ "model_architectures": "GPT2LMHeadModel" }, { - "description": "MaziyarPanahi/japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1-GGUF Model creator: MaziyarPanahi Original model: MaziyarPanahi/japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1 Description MaziyarPanahi/japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1-GGUF contains GGUF format model files for MaziyarPanahi/japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1.", - "url": "https://huggingface.co/MaziyarPanahi/japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1-GGUF", - "project_name": "japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1-GGUF", - "downloads": 125, - "source": "Hugging Face", - "score": -0.11248197788842262, - "first_commit": "2024-01-28 16:13:26", - "latest_commit": "2024-01-28 16:24:30", - "languages": [], - "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": null - }, - { - "description": "Orion-14B 🌐English | 🇨", - "url": "https://huggingface.co/OrionStarAI/Orion-14B-Chat-RAG", - "project_name": "Orion-14B-Chat-RAG", + "description": "mbpp-ja", + "url": "https://huggingface.co/datasets/llm-jp/mbpp-ja", + "project_name": "mbpp-ja", "downloads": 124, "source": "Hugging Face", - "score": -0.11249768924511684, - "first_commit": "2024-01-16 12:19:08", - "latest_commit": "2024-03-26 10:08:09", + "score": -0.09147998870975292, + "first_commit": "2024-04-19 00:26:56", + "latest_commit": "2024-04-20 06:26:51", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "OrionForCausalLM" + "model_architectures": null }, { - "description": "deberta-large-japanese-aozora Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-aozora", - "project_name": "deberta-large-japanese-aozora", + "description": "gemma-2-2b-it-gguf googleさんが公開しているgemma-2-2b-itのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/gemma-2-2b-it-gguf", + "project_name": "gemma-2-2b-it-gguf", "downloads": 123, "source": "Hugging Face", - "score": -0.11251340060181106, - "first_commit": "2022-05-26 14:46:58", - "latest_commit": "2023-01-14 00:27:22", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "DebertaV2ForMaskedLM" - }, - { - "description": "Model Card for Japanese character-level GPT-2 Small Model description This is a Japanese character-level GPT-2 Small (90M parameters) language model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.", - "url": "https://huggingface.co/ku-nlp/gpt2-small-japanese-char", - "project_name": "gpt2-small-japanese-char", - "downloads": 120, - "source": "Hugging Face", - "score": -0.11256053467189371, - "first_commit": "2023-04-18 08:24:55", - "latest_commit": "2023-05-08 10:08:13", - "languages": [], - "model_or_dataset": "model", - "model_size": 0.10300000000000001, - "model_architectures": "GPT2LMHeadModel" - }, - { - "description": "whisper-large-v3-japanese-4k-steps This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 16.1 dataset.", - "url": "https://huggingface.co/drewschaub/whisper-large-v3-japanese-4k-steps", - "project_name": "whisper-large-v3-japanese-4k-steps", - "downloads": 118, - "source": "Hugging Face", - "score": -0.11259195738528215, - "first_commit": "2024-02-17 01:01:51", - "latest_commit": "2024-02-18 01:31:35", + "score": -0.09149059366028925, + "first_commit": "2024-08-01 17:22:58", + "latest_commit": "2024-08-01 18:29:08", "languages": [], "model_or_dataset": "model", - "model_size": 1.54, - "model_architectures": "WhisperForConditionalGeneration" + "model_size": 2.61, + "model_architectures": null }, { - "description": "WRIME-fine-tuned BERT base Japanese This model is a Japanese BERTBASE fine-tuned on the WRIME dataset.", - "url": "https://huggingface.co/patrickramos/bert-base-japanese-v2-wrime-fine-tune", - "project_name": "bert-base-japanese-v2-wrime-fine-tune", - "downloads": 118, + "description": "This dataset is a clarified version of the image, context, and question set included in the Japanese-Heron-Bench for the construction of the Japanese evaluation benchmark suite.", + "url": "https://huggingface.co/datasets/Silviase/Japanese-Heron-Bench", + "project_name": "Japanese-Heron-Bench", + "downloads": 123, "source": "Hugging Face", - "score": -0.11259195738528215, - "first_commit": "2022-05-22 09:42:14", - "latest_commit": "2023-03-22 08:11:34", + "score": -0.09149059366028925, + "first_commit": "2024-07-16 08:12:30", + "latest_commit": "2024-07-28 12:33:15", "languages": [], - "model_or_dataset": "model", - "model_size": 0.111, - "model_architectures": "BertForSequenceClassification" + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null }, { "description": "モデルの説明(English explanation is below.", "url": "https://huggingface.co/keitokei1994/Llama-3-ELYZA-sqlcoder-2x8B-GGUF", "project_name": "Llama-3-ELYZA-sqlcoder-2x8B-GGUF", - "downloads": 117, + "downloads": 122, "source": "Hugging Face", - "score": -0.11260766874197636, + "score": -0.09150119861082559, "first_commit": "2024-06-28 01:51:50", "latest_commit": "2024-06-28 05:56:23", "languages": [], @@ -8476,200 +8409,158 @@ "model_architectures": null }, { - "description": "[github].", - "url": "https://huggingface.co/datasets/fujiki/japanese_alpaca_data", - "project_name": "japanese_alpaca_data", - "downloads": 117, + "description": "ELYZA-japanese-CodeLlama-7b-gguf ELYZAさんが公開しているELYZA-japanese-CodeLlama-7b-instructのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/ELYZA-japanese-CodeLlama-7b-gguf", + "project_name": "ELYZA-japanese-CodeLlama-7b-gguf", + "downloads": 120, "source": "Hugging Face", - "score": -0.11260766874197636, - "first_commit": "2023-05-18 07:13:15", - "latest_commit": "2023-05-19 12:54:13", + "score": -0.09152240851189826, + "first_commit": "2023-11-15 09:53:42", + "latest_commit": "2023-11-16 14:28:03", + "languages": [], + "model_or_dataset": "model", + "model_size": 6.74, + "model_architectures": null + }, + { + "description": "Update: 2023/12/25oasst2-135k-jaをチャット形式に変換したoasst2-chat-68k-jaを公開しました。 ", + "url": "https://huggingface.co/datasets/kunishou/oasst2-135k-ja", + "project_name": "oasst2-135k-ja", + "downloads": 116, + "source": "Hugging Face", + "score": -0.09156482831404358, + "first_commit": "2023-12-24 22:04:54", + "latest_commit": "2023-12-25 13:23:55", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "DataPilot様の ArrowPro-7B-RobinHood をGGUF形式に変換したものです。 ", - "url": "https://huggingface.co/MCZK/ArrowPro-7B-RobinHood-GGUF", - "project_name": "ArrowPro-7B-RobinHood-GGUF", + "description": "abc-multiple-choice Dataset abc-multiple-choice は、競技クイズの大会「abc」で使用された4択問題を元に作成された、多肢選択式の質問応答データセットです。 ", + "url": "https://huggingface.co/datasets/tohoku-nlp/abc-multiple-choice", + "project_name": "abc-multiple-choice", "downloads": 116, "source": "Hugging Face", - "score": -0.11262338009867058, - "first_commit": "2024-05-10 12:03:26", - "latest_commit": "2024-05-10 18:14:28", + "score": -0.09156482831404358, + "first_commit": "2024-03-02 03:58:25", + "latest_commit": "2024-03-12 07:32:13", "languages": [], - "model_or_dataset": "model", - "model_size": 7.24, + "model_or_dataset": "dataset", + "model_size": null, "model_architectures": null }, { - "description": "ryota39様の Tora-7B-v0.2 をGGUF形式に変換したものです。 ", - "url": "https://huggingface.co/MCZK/Tora-7B-v0.2-GGUF", - "project_name": "Tora-7B-v0.2-GGUF", - "downloads": 115, + "description": "Llama-3-EZO-VLM-1 Based on SakanaAI/Llama-3-EvoVLM-JP-v2, it has been enhanced for Japanese usage through additional pre-training and instruction tuning.", + "url": "https://huggingface.co/AXCXEPT/Llama-3-EZO-VLM-1", + "project_name": "Llama-3-EZO-VLM-1", + "downloads": 114, "source": "Hugging Face", - "score": -0.1126390914553648, - "first_commit": "2024-05-06 12:50:49", - "latest_commit": "2024-06-15 03:17:32", + "score": -0.09158603821511625, + "first_commit": "2024-08-03 17:15:09", + "latest_commit": "2024-08-23 10:55:53", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": null - }, - { - "description": "Japanese stopwords for nagisa", - "url": "https://huggingface.co/datasets/taishi-i/nagisa_stopwords", - "project_name": "nagisa_stopwords", - "downloads": 115, - "source": "Hugging Face", - "score": -0.1126390914553648, - "first_commit": "2023-08-06 17:10:10", - "latest_commit": "2023-08-07 02:58:31", - "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null - }, - { - "description": "mbpp-ja", - "url": "https://huggingface.co/datasets/llm-jp/mbpp-ja", - "project_name": "mbpp-ja", - "downloads": 115, - "source": "Hugging Face", - "score": -0.1126390914553648, - "first_commit": "2024-04-19 00:26:56", - "latest_commit": "2024-04-20 06:26:51", - "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null + "model_size": 8.48, + "model_architectures": "LlavaForConditionalGeneration" }, { - "description": "275.86Mのmixtralを日本語データセットでpretrainingしたものです sample from transformers import AutoTokenizer, AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained(\"if001/tiny_mixtral_ja\")", - "url": "https://huggingface.co/if001/tiny_mixtral_ja", - "project_name": "tiny_mixtral_ja", - "downloads": 114, + "description": "Tanuki-8B-dpo-v1.0-AWQ 概要 GENIAC 松尾研 LLM開発プロジェクトで開発されたLLMであるweblab-GENIAC/Tanuki-8B-dpo-v1.0のAWQ 4bit量子化モデルです。", + "url": "https://huggingface.co/team-hatakeyama-phase2/Tanuki-8B-dpo-v1.0-AWQ", + "project_name": "Tanuki-8B-dpo-v1.0-AWQ", + "downloads": 113, "source": "Hugging Face", - "score": -0.112654802812059, - "first_commit": "2024-01-22 15:02:21", - "latest_commit": "2024-01-23 00:42:05", + "score": -0.0915966431656526, + "first_commit": "2024-08-27 04:50:35", + "latest_commit": "2024-09-03 09:29:23", "languages": [], "model_or_dataset": "model", - "model_size": 0.276, - "model_architectures": "MixtralForCausalLM" + "model_size": 1.47, + "model_architectures": "LlamaForCausalLM" }, { - "description": "QuantFactory/shisa-gamma-7b-v1-GGUF", - "url": "https://huggingface.co/QuantFactory/shisa-gamma-7b-v1-GGUF", - "project_name": "shisa-gamma-7b-v1-GGUF", + "description": "ELYZA-japanese-CodeLlama-7b Model Description ELYZA-japanese-CodeLlama-7b は、 Code Llamaをベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。 ", + "url": "https://huggingface.co/elyza/ELYZA-japanese-CodeLlama-7b", + "project_name": "ELYZA-japanese-CodeLlama-7b", "downloads": 113, "source": "Hugging Face", - "score": -0.11267051416875322, - "first_commit": "2024-06-12 17:16:36", - "latest_commit": "2024-06-18 06:17:30", + "score": -0.0915966431656526, + "first_commit": "2023-11-07 12:48:15", + "latest_commit": "2023-11-15 00:38:12", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": null + "model_size": 6.74, + "model_architectures": "LlamaForCausalLM" }, { - "description": "更新履歴 2023年5月7日 「oasst1-89k-ja」データセットを追加して対話システムに対応しました。", - "url": "https://huggingface.co/inu-ai/dolly-japanese-gpt-1b", - "project_name": "dolly-japanese-gpt-1b", - "downloads": 111, + "description": "モデル概要 AWSのtrn1インスタンスを用いて開発した大喜利言語モデルです。", + "url": "https://huggingface.co/watashiha/watashiha-gpt-6b", + "project_name": "watashiha-gpt-6b", + "downloads": 112, "source": "Hugging Face", - "score": -0.11270193688214165, - "first_commit": "2023-04-13 22:46:07", - "latest_commit": "2023-08-01 07:55:27", + "score": -0.09160724811618892, + "first_commit": "2023-12-28 05:41:38", + "latest_commit": "2024-03-04 05:21:14", "languages": [], "model_or_dataset": "model", - "model_size": 1.33, + "model_size": 5.83, "model_architectures": "GPT2LMHeadModel" }, { - "description": "oasst2-33k-ja This repository provides an instruction tuning dataset developed by LLM-jp, a collaborative project launched in Japan.", - "url": "https://huggingface.co/datasets/llm-jp/oasst2-33k-ja", - "project_name": "oasst2-33k-ja", + "description": "doc2query/msmarco-japanese-mt5-base-v1 This is a doc2query model based on mT5 (also known as docT5query).", + "url": "https://huggingface.co/doc2query/msmarco-japanese-mt5-base-v1", + "project_name": "msmarco-japanese-mt5-base-v1", "downloads": 111, "source": "Hugging Face", - "score": -0.11270193688214165, - "first_commit": "2024-04-28 16:24:00", - "latest_commit": "2024-04-28 16:39:03", + "score": -0.09161785306672526, + "first_commit": "2022-04-29 12:05:21", + "latest_commit": "2022-04-29 14:05:37", "languages": [], - "model_or_dataset": "dataset", + "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "MT5ForConditionalGeneration" }, { - "description": "Japanese-TextGen-Kage-v0.1-2x7B Kage is \"影\" in Japanese or \"Shadow\" in English.", - "url": "https://huggingface.co/dddump/Japanese-TextGen-Kage-v0.1-2x7B-gguf", - "project_name": "Japanese-TextGen-Kage-v0.1-2x7B-gguf", + "description": "MaziyarPanahi/japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1-GGUF Model creator: MaziyarPanahi Original model: MaziyarPanahi/japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1 Description MaziyarPanahi/japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1-GGUF contains GGUF format model files for MaziyarPanahi/japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1.", + "url": "https://huggingface.co/MaziyarPanahi/japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1-GGUF", + "project_name": "japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1-GGUF", "downloads": 110, "source": "Hugging Face", - "score": -0.11271764823883587, - "first_commit": "2024-05-04 07:03:38", - "latest_commit": "2024-05-19 08:54:19", + "score": -0.09162845801726159, + "first_commit": "2024-01-28 16:13:26", + "latest_commit": "2024-01-28 16:24:30", "languages": [], "model_or_dataset": "model", - "model_size": 12.9, + "model_size": 7.24, "model_architectures": null }, { - "description": "line-corporation/japanese-large-lm-3.6b-instruction-sft line-corporationさんが公開しているjapanese-large-lm-3.6b-instruction-sftのgguf変換版です。 ", - "url": "https://huggingface.co/mmnga/line-corp-japanese-large-lm-3.6b-instruction-sft-gguf", - "project_name": "line-corp-japanese-large-lm-3.6b-instruction-sft-gguf", + "description": "MaziyarPanahi/japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1-GGUF Model creator: MaziyarPanahi Original model: MaziyarPanahi/japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1 Description MaziyarPanahi/japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1-GGUF contains GGUF format model files for MaziyarPanahi/japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1.", + "url": "https://huggingface.co/MaziyarPanahi/japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1-GGUF", + "project_name": "japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1-GGUF", "downloads": 110, "source": "Hugging Face", - "score": -0.11271764823883587, - "first_commit": "2023-09-02 18:01:40", - "latest_commit": "2023-09-08 02:52:29", - "languages": [], - "model_or_dataset": "model", - "model_size": 3.71, - "model_architectures": null - }, - { - "description": "モデル概要 AWSのtrn1インスタンスを用いて開発した大喜利言語モデルです。", - "url": "https://huggingface.co/watashiha/watashiha-gpt-6b", - "project_name": "watashiha-gpt-6b", - "downloads": 109, - "source": "Hugging Face", - "score": -0.11273335959553009, - "first_commit": "2023-12-28 05:41:38", - "latest_commit": "2024-03-04 05:21:14", - "languages": [], - "model_or_dataset": "model", - "model_size": 5.83, - "model_architectures": "GPT2LMHeadModel" - }, - { - "description": "c4ai-command-r-v01-japanese-instruct-GGUF 概要 Aratako/c4ai-command-r-v01-japanese-instructの量子化済みGGUF版です。", - "url": "https://huggingface.co/Aratako/c4ai-command-r-v01-japanese-instruct-GGUF", - "project_name": "c4ai-command-r-v01-japanese-instruct-GGUF", - "downloads": 109, - "source": "Hugging Face", - "score": -0.11273335959553009, - "first_commit": "2024-04-05 17:10:51", - "latest_commit": "2024-04-07 03:19:34", + "score": -0.09162845801726159, + "first_commit": "2024-01-26 06:13:55", + "latest_commit": "2024-01-26 06:36:22", "languages": [], "model_or_dataset": "model", - "model_size": 35.0, + "model_size": 7.24, "model_architectures": null }, { - "description": "[EZO model card]", - "url": "https://huggingface.co/AXCXEPT/EZO-InternVL2-26B", - "project_name": "EZO-InternVL2-26B", + "description": "Aerner LM-v2 事前学習から全部日本語で学習させたモデルのバージョン2です。 ", + "url": "https://huggingface.co/aerner/lm-v2", + "project_name": "lm-v2", "downloads": 109, "source": "Hugging Face", - "score": -0.11273335959553009, - "first_commit": "2024-08-19 08:03:55", - "latest_commit": "2024-08-23 10:56:47", + "score": -0.09163906296779792, + "first_commit": "2023-06-09 15:19:12", + "latest_commit": "2023-06-09 16:08:47", "languages": [], "model_or_dataset": "model", - "model_size": 25.5, - "model_architectures": "InternVLChatModel" + "model_size": null, + "model_architectures": "OpenLlamaForCausalLM" }, { "description": "LLM-jp Toxicity Dataset 日本語���害文書データセット「LLM-jp Toxicity Dataset」 See https://gitlab.llm-jp.nii.ac.jp/datasets/llm-jp-toxicity-dataset", @@ -8677,7 +8568,7 @@ "project_name": "LLM-jp-Toxicity-Dataset", "downloads": 109, "source": "Hugging Face", - "score": -0.11273335959553009, + "score": -0.09163906296779792, "first_commit": "2024-08-07 07:11:08", "latest_commit": "2024-08-07 07:21:07", "languages": [], @@ -8686,222 +8577,194 @@ "model_architectures": null }, { - "description": "AutoWikiQA 東工大が公開しているSwallow-MXを用いて、Wikipedia中のテキストを入力として「質問(query)」と「回答(answer)」を生成し、生成された質問と回答についてフィルタリングを行ったデータセットです。", - "url": "https://huggingface.co/datasets/cl-nagoya/auto-wiki-qa", - "project_name": "auto-wiki-qa", - "downloads": 109, + "description": "Anime with caption CC-0 dataset このデータセットはイラストに対する日本語キャプションを 倫理的に学習しやすくするためのデータセットです。 ", + "url": "https://huggingface.co/datasets/alfredplpl/anime-with-caption-cc0", + "project_name": "anime-with-caption-cc0", + "downloads": 108, "source": "Hugging Face", - "score": -0.11273335959553009, - "first_commit": "2024-03-28 01:33:42", - "latest_commit": "2024-04-20 12:17:33", + "score": -0.09164966791833426, + "first_commit": "2024-06-03 04:37:13", + "latest_commit": "2024-06-03 05:49:20", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "Wikidata parallel descriptions en-ja Parallel corpus for machine translation generated from wikidata dump (2024-05-06).", - "url": "https://huggingface.co/datasets/Mitsua/wikidata-parallel-descriptions-en-ja", - "project_name": "wikidata-parallel-descriptions-en-ja", - "downloads": 109, + "description": "Dataset.", + "url": "https://huggingface.co/datasets/hpprc/jsick", + "project_name": "jsick", + "downloads": 108, "source": "Hugging Face", - "score": -0.11273335959553009, - "first_commit": "2024-05-13 12:02:43", - "latest_commit": "2024-05-17 00:25:10", + "score": -0.09164966791833426, + "first_commit": "2023-04-08 16:02:06", + "latest_commit": "2023-04-11 15:18:09", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "Update: 2023/12/25oasst2-135k-jaをチャット形式に変換したoasst2-chat-68k-jaを公開しました。 ", - "url": "https://huggingface.co/datasets/kunishou/oasst2-135k-ja", - "project_name": "oasst2-135k-ja", - "downloads": 108, + "description": "Ruri-Reranker: Japanese General Reranker Usage Direct Usage (Sentence Transformers)", + "url": "https://huggingface.co/cl-nagoya/ruri-reranker-large", + "project_name": "ruri-reranker-large", + "downloads": 106, "source": "Hugging Face", - "score": -0.1127490709522243, - "first_commit": "2023-12-24 22:04:54", - "latest_commit": "2023-12-25 13:23:55", + "score": -0.09167087781940693, + "first_commit": "2024-08-20 02:37:26", + "latest_commit": "2024-09-04 08:50:12", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null + "model_or_dataset": "model", + "model_size": 0.337, + "model_architectures": "BertForSequenceClassification" }, { - "description": "Orion-14B 🌐English | 🇨", - "url": "https://huggingface.co/OrionStarAI/Orion-14B-Chat-Int4", - "project_name": "Orion-14B-Chat-Int4", - "downloads": 107, + "description": "Japanese-TextGen-Kage-v0.1-2x7B Kage is \"影\" in Japanese or \"Shadow\" in English.", + "url": "https://huggingface.co/dddump/Japanese-TextGen-Kage-v0.1-2x7B-gguf", + "project_name": "Japanese-TextGen-Kage-v0.1-2x7B-gguf", + "downloads": 106, "source": "Hugging Face", - "score": -0.11276478230891852, - "first_commit": "2024-01-18 09:54:07", - "latest_commit": "2024-03-26 10:04:46", + "score": -0.09167087781940693, + "first_commit": "2024-05-04 07:03:38", + "latest_commit": "2024-05-19 08:54:19", "languages": [], "model_or_dataset": "model", - "model_size": 2.69, - "model_architectures": "OrionForCausalLM" + "model_size": 12.9, + "model_architectures": null }, { - "description": "doc2query/msmarco-japanese-mt5-base-v1 This is a doc2query model based on mT5 (also known as docT5query).", - "url": "https://huggingface.co/doc2query/msmarco-japanese-mt5-base-v1", - "project_name": "msmarco-japanese-mt5-base-v1", + "description": "Japanese Anime Speech Dataset V2 日本語はこちら japanese-anime-speech-v2 is an audio-text dataset designed for training automatic speech recognition models.", + "url": "https://huggingface.co/datasets/joujiboi/japanese-anime-speech-v2", + "project_name": "japanese-anime-speech-v2", "downloads": 106, "source": "Hugging Face", - "score": -0.11278049366561274, - "first_commit": "2022-04-29 12:05:21", - "latest_commit": "2022-04-29 14:05:37", + "score": -0.09167087781940693, + "first_commit": "2024-06-26 14:18:01", + "latest_commit": "2024-07-24 19:06:51", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "MT5ForConditionalGeneration" + "model_architectures": null }, { - "description": "Tanuki-ZeRo-gguf kanhatakeyamaさんが公開しているTanuki-ZeRoのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Tanuki-ZeRo-gguf", - "project_name": "Tanuki-ZeRo-gguf", - "downloads": 104, + "description": "Japanese stopwords for nagisa", + "url": "https://huggingface.co/datasets/taishi-i/nagisa_stopwords", + "project_name": "nagisa_stopwords", + "downloads": 106, "source": "Hugging Face", - "score": -0.11281191637900118, - "first_commit": "2024-03-30 10:49:02", - "latest_commit": "2024-03-30 17:01:16", + "score": -0.09167087781940693, + "first_commit": "2023-08-06 17:10:10", + "latest_commit": "2023-08-07 02:58:31", "languages": [], - "model_or_dataset": "model", - "model_size": 13.1, + "model_or_dataset": "dataset", + "model_size": null, "model_architectures": null }, { - "description": "ELYZA-japanese-CodeLlama-7b Model Description ELYZA-japanese-CodeLlama-7b は、 Code Llamaをベースとして日本語能力を拡張するために追加事前学習を行ったモデルです。 ", - "url": "https://huggingface.co/elyza/ELYZA-japanese-CodeLlama-7b", - "project_name": "ELYZA-japanese-CodeLlama-7b", + "description": "Japanese InstructBLIP Alpha Model Details Japanese InstructBLIP Alpha is a vision-language instruction-following model that enables to generate Japanese descriptions for input images and optionally input texts such as questions.", + "url": "https://huggingface.co/stabilityai/japanese-instructblip-alpha", + "project_name": "japanese-instructblip-alpha", "downloads": 104, "source": "Hugging Face", - "score": -0.11281191637900118, - "first_commit": "2023-11-07 12:48:15", - "latest_commit": "2023-11-15 00:38:12", + "score": -0.0916920877204796, + "first_commit": "2023-08-16 23:49:58", + "latest_commit": "2023-11-17 03:57:41", "languages": [], "model_or_dataset": "model", - "model_size": 6.74, - "model_architectures": "LlamaForCausalLM" + "model_size": null, + "model_architectures": "JapaneseInstructBlipAlphaForConditionalGeneration" }, { - "description": "AIBunCho/japanese-novel-gpt-j-6b AI BunChoで利用しているモデルです。", - "url": "https://huggingface.co/AIBunCho/japanese-novel-gpt-j-6b", - "project_name": "japanese-novel-gpt-j-6b", - "downloads": 100, - "source": "Hugging Face", - "score": -0.11287476180577805, - "first_commit": "2023-08-11 00:52:32", - "latest_commit": "2023-08-26 04:20:51", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "GPTJForCausalLM" - }, - { - "description": "Vecteus-V2-7B このモデルは、ベクトルマージなどを用い作成された高性能ベースモデルです。 ", - "url": "https://huggingface.co/Local-Novel-LLM-project/Vecteus-V2-7B", - "project_name": "Vecteus-V2-7B", - "downloads": 100, + "description": "SentenceTransformer based on line-corporation/line-distilbert-base-japanese This is a sentence-transformers model finetuned from line-corporation/line-distilbert-base-japanese.", + "url": "https://huggingface.co/cl-nagoya/ruri-pt-small", + "project_name": "ruri-pt-small", + "downloads": 104, "source": "Hugging Face", - "score": -0.11287476180577805, - "first_commit": "2024-06-16 03:51:43", - "latest_commit": "2024-07-06 13:39:41", + "score": -0.0916920877204796, + "first_commit": "2024-08-17 10:39:05", + "latest_commit": "2024-08-30 03:11:20", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": "MistralForCausalLM" + "model_size": 0.0681, + "model_architectures": "DistilBertModel" }, { - "description": "日本語 gpt2 蒸留モデル このモデルはrinna/japanese-gpt2-meduimを教師として蒸留したものです。 ", - "url": "https://huggingface.co/knok/japanese-distilgpt2", - "project_name": "japanese-distilgpt2", - "downloads": 99, + "description": "Model card for model ID", + "url": "https://huggingface.co/retrieva-jp/t5-base-medium", + "project_name": "t5-base-medium", + "downloads": 103, "source": "Hugging Face", - "score": -0.11289047316247226, - "first_commit": "2022-04-14 09:32:23", - "latest_commit": "2022-04-15 06:00:51", + "score": -0.09170269267101593, + "first_commit": "2023-04-26 08:27:09", + "latest_commit": "2023-05-10 10:00:12", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": null - }, - { - "description": "fio-base-japanese-v0.1 日本語版は近日公開予定です（日本語を勉強中なので、間違いはご容赦ください！", - "url": "https://huggingface.co/bclavie/fio-base-japanese-v0.1", - "project_name": "fio-base-japanese-v0.1", - "downloads": 98, - "source": "Hugging Face", - "score": -0.11290618451916648, - "first_commit": "2023-12-18 11:01:07", - "latest_commit": "2023-12-19 10:28:16", - "languages": [], - "model_or_dataset": "model", - "model_size": 0.111, - "model_architectures": "BertModel" + "model_architectures": "T5ForConditionalGeneration" }, { - "description": "Tanuki-8x8B-dpo-v1.0-GPTQ-4bit 概要 GENIAC 松尾研 LLM開発プロジェクトで開発されたLLMであるweblab-GENIAC/Tanuki-8x8B-dpo-v1.0のGPTQ 4bit量子化モデルです。", - "url": "https://huggingface.co/team-hatakeyama-phase2/Tanuki-8x8B-dpo-v1.0-GPTQ-4bit", - "project_name": "Tanuki-8x8B-dpo-v1.0-GPTQ-4bit", - "downloads": 98, + "description": "RoBERTa base Japanese - JaQuAD Description A Japanese Question Answering model fine-tuned on JaQuAD.", + "url": "https://huggingface.co/ybelkada/japanese-roberta-question-answering", + "project_name": "japanese-roberta-question-answering", + "downloads": 101, "source": "Hugging Face", - "score": -0.11290618451916648, - "first_commit": "2024-08-27 18:19:13", - "latest_commit": "2024-09-03 09:27:14", + "score": -0.0917239025720886, + "first_commit": "2022-04-08 08:52:22", + "latest_commit": "2022-04-08 11:38:39", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "TanukiForCausalLM" + "model_architectures": "RobertaForQuestionAnswering" }, { - "description": "Japanese ELECTRA-small We provide a Japanese ELECTRA-Small model, as described in ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators.", - "url": "https://huggingface.co/cinmodel/electra-small-japanese-discriminator", - "project_name": "electra-small-japanese-discriminator", - "downloads": 97, + "description": "albert-base-japanese-v1-with-japanese 日本語事前学習済みALBERTモデルですこのモデルではTokenizerにBertJapaneseTokenizerクラスを利用していますalbert-base-japanese-v1よりトークナイズ処理が楽になっています How to use ファインチューニング このモデルはPreTrainedモデルです基本的には各種タスク用にファインチューニングして使用されることを想定しています Fill-Mask for PyTorch from transformers import ( AutoModelForMaskedLM, AutoTokenizer ) tokenizer = AutoTokenizer.from_pretrained(\"ken11/albert-base-japanese-v1-with-japanese-tokenizer\")", + "url": "https://huggingface.co/ken11/albert-base-japanese-v1-with-japanese-tokenizer", + "project_name": "albert-base-japanese-v1-with-japanese-tokenizer", + "downloads": 100, "source": "Hugging Face", - "score": -0.1129218958758607, - "first_commit": "2020-11-13 06:49:25", - "latest_commit": "2020-12-11 22:26:13", + "score": -0.09173450752262494, + "first_commit": "2022-04-20 16:34:22", + "latest_commit": "2022-04-21 02:28:13", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "ElectraForPreTraining" + "model_architectures": "AlbertForMaskedLM" }, { - "description": "deberta-base-japanese-aozora-ud-head Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-aozora-ud-head", - "project_name": "deberta-base-japanese-aozora-ud-head", - "downloads": 96, + "description": "Wikidata parallel descriptions en-ja Parallel corpus for machine translation generated from wikidata dump (2024-05-06).", + "url": "https://huggingface.co/datasets/Mitsua/wikidata-parallel-descriptions-en-ja", + "project_name": "wikidata-parallel-descriptions-en-ja", + "downloads": 100, "source": "Hugging Face", - "score": -0.11293760723255492, - "first_commit": "2022-06-15 04:02:27", - "latest_commit": "2023-03-04 20:10:16", + "score": -0.09173450752262494, + "first_commit": "2024-05-13 12:02:43", + "latest_commit": "2024-05-17 00:25:10", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "DebertaV2ForQuestionAnswering" + "model_architectures": null }, { - "description": "RoBERTa base Japanese - JaQuAD Description A Japanese Question Answering model fine-tuned on JaQuAD.", - "url": "https://huggingface.co/ybelkada/japanese-roberta-question-answering", - "project_name": "japanese-roberta-question-answering", - "downloads": 96, + "description": "Tanuki-ZeRo-gguf kanhatakeyamaさんが公開しているTanuki-ZeRoのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Tanuki-ZeRo-gguf", + "project_name": "Tanuki-ZeRo-gguf", + "downloads": 99, "source": "Hugging Face", - "score": -0.11293760723255492, - "first_commit": "2022-04-08 08:52:22", - "latest_commit": "2022-04-08 11:38:39", + "score": -0.09174511247316126, + "first_commit": "2024-03-30 10:49:02", + "latest_commit": "2024-03-30 17:01:16", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "RobertaForQuestionAnswering" + "model_size": 13.1, + "model_architectures": null }, { "description": "Ninja-v1-RP-GGUF 概要 Aratako/Ninja-v1-RPの量子化済みGGUF版です。", "url": "https://huggingface.co/Aratako/Ninja-v1-RP-GGUF", "project_name": "Ninja-v1-RP-GGUF", - "downloads": 95, + "downloads": 99, "source": "Hugging Face", - "score": -0.11295331858924913, + "score": -0.09174511247316126, "first_commit": "2024-05-20 17:08:50", "latest_commit": "2024-05-24 15:11:08", "languages": [], @@ -8910,82 +8773,96 @@ "model_architectures": null }, { - "description": "nlp-waseda/roberta-large-japanese Model description This is a Japanese RoBERTa large model pretrained on Japanese Wikipedia and the Japanese portion of CC-100.", - "url": "https://huggingface.co/nlp-waseda/roberta-large-japanese", - "project_name": "roberta-large-japanese", - "downloads": 95, + "description": "This model is traned with guanaco dataset.", + "url": "https://huggingface.co/ganchengguang/Yoko-7B-Japanese-v0", + "project_name": "Yoko-7B-Japanese-v0", + "downloads": 99, "source": "Hugging Face", - "score": -0.11295331858924913, - "first_commit": "2022-05-10 08:37:48", - "latest_commit": "2022-10-21 14:48:46", + "score": -0.09174511247316126, + "first_commit": "2023-08-09 16:28:38", + "latest_commit": "2023-08-10 13:00:34", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "RobertaForMaskedLM" + "model_architectures": "LlamaForCausalLM" }, { - "description": "Japanese ELECTRA-small We provide a Japanese ELECTRA-Small model, as described in ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators.", - "url": "https://huggingface.co/cinmodel/electra-small-japanese-generator", - "project_name": "electra-small-japanese-generator", - "downloads": 94, + "description": "日本語 gpt2 蒸留モデル このモデルはrinna/japanese-gpt2-meduimを教師として蒸留したものです。 ", + "url": "https://huggingface.co/knok/japanese-distilgpt2", + "project_name": "japanese-distilgpt2", + "downloads": 96, "source": "Hugging Face", - "score": -0.11296902994594335, - "first_commit": "2020-11-13 06:49:52", - "latest_commit": "2020-12-11 22:26:17", + "score": -0.09177692732477026, + "first_commit": "2022-04-14 09:32:23", + "latest_commit": "2022-04-15 06:00:51", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "ElectraForMaskedLM" + "model_architectures": null }, { - "description": "reazonspeech-espnet-next ReazonSpeech is a project to maintain freely-available Japanese audio datasets and ML models.", - "url": "https://huggingface.co/reazon-research/reazonspeech-espnet-next", - "project_name": "reazonspeech-espnet-next", - "downloads": 94, + "description": "sonoisa/t5-base-japaneseをファインチューニングして、タイトル生成に用いれるようにしたモデルです。 ", + "url": "https://huggingface.co/Mizuiro-sakura/t5-CAMERA-title-generation", + "project_name": "t5-CAMERA-title-generation", + "downloads": 96, "source": "Hugging Face", - "score": -0.11296902994594335, - "first_commit": "2023-03-29 07:20:03", - "latest_commit": "2023-03-29 17:28:01", + "score": -0.09177692732477026, + "first_commit": "2023-03-21 10:49:27", + "latest_commit": "2023-07-21 14:11:13", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.223, + "model_architectures": "T5ForConditionalGeneration" + }, + { + "description": "日本語VL-T5事前学習済みモデル", + "url": "https://huggingface.co/sonoisa/vl-t5-base-japanese", + "project_name": "vl-t5-base-japanese", + "downloads": 96, + "source": "Hugging Face", + "score": -0.09177692732477026, + "first_commit": "2021-10-03 11:54:43", + "latest_commit": "2021-10-04 11:13:35", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "VLT5ModelWrapper" }, { - "description": "Llama-3-8B-Instruct-JP-nk2t-v0.2 Model Details: Built with Meta Llama 3", - "url": "https://huggingface.co/nk2t/Llama-3-8B-Instruct-japanese-nk2t-v0.2", - "project_name": "Llama-3-8B-Instruct-japanese-nk2t-v0.2", - "downloads": 92, + "description": "更新履歴 2023年5月7日 「oasst1-89k-ja」データセットを追加して対話システムに対応しました。", + "url": "https://huggingface.co/inu-ai/dolly-japanese-gpt-1b", + "project_name": "dolly-japanese-gpt-1b", + "downloads": 95, "source": "Hugging Face", - "score": -0.11300045265933178, - "first_commit": "2024-05-04 04:16:35", - "latest_commit": "2024-05-15 12:56:34", + "score": -0.0917875322753066, + "first_commit": "2023-04-13 22:46:07", + "latest_commit": "2023-08-01 07:55:27", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": "LlamaForCausalLM" + "model_size": 1.33, + "model_architectures": "GPT2LMHeadModel" }, { - "description": "Finetuned Waseda RoBERTa to evaluate the generated answers on JTruthfulQA.", - "url": "https://huggingface.co/nlp-waseda/roberta_jtruthfulqa", - "project_name": "roberta_jtruthfulqa", - "downloads": 90, + "description": "roberta-long-japanese (jumanpp + sentencepiece, mC4 Japanese)", + "url": "https://huggingface.co/megagonlabs/roberta-long-japanese", + "project_name": "roberta-long-japanese", + "downloads": 95, "source": "Hugging Face", - "score": -0.11303187537272022, - "first_commit": "2023-12-06 01:33:02", - "latest_commit": "2023-12-06 04:31:12", + "score": -0.0917875322753066, + "first_commit": "2022-09-04 14:31:06", + "latest_commit": "2022-10-04 23:36:27", "languages": [], "model_or_dataset": "model", - "model_size": 0.337, - "model_architectures": "RobertaForSequenceClassification" + "model_size": null, + "model_architectures": "RobertaForMaskedLM" }, { "description": "umiyuki様の Japanese-Chat-Umievo-itr004-7b をGGUF形式に変換したものです。 ", "url": "https://huggingface.co/MCZK/Japanese-Chat-Umievo-itr004-7b-GGUF", "project_name": "Japanese-Chat-Umievo-itr004-7b-GGUF", - "downloads": 89, + "downloads": 94, "source": "Hugging Face", - "score": -0.11304758672941444, + "score": -0.09179813722584293, "first_commit": "2024-05-13 16:28:41", "latest_commit": "2024-05-13 23:33:49", "languages": [], @@ -8994,96 +8871,152 @@ "model_architectures": null }, { - "description": "Local-Novel-LLM-project様の Ninja-V3 をGGUF形式に変換したものです。 ", - "url": "https://huggingface.co/MCZK/Ninja-V3-GGUF", - "project_name": "Ninja-V3-GGUF", - "downloads": 88, + "description": "deberta-base-japanese-aozora-ud-head Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-aozora-ud-head", + "project_name": "deberta-base-japanese-aozora-ud-head", + "downloads": 93, "source": "Hugging Face", - "score": -0.11306329808610865, - "first_commit": "2024-07-03 11:52:04", - "latest_commit": "2024-07-03 16:59:05", + "score": -0.09180874217637927, + "first_commit": "2022-06-15 04:02:27", + "latest_commit": "2023-03-04 20:10:16", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": null + "model_size": null, + "model_architectures": "DebertaV2ForQuestionAnswering" }, { - "description": "Japanese-LLaMA-3-8B-Instruct-v2 Japanese-LLaMA-3-8B-Instruct-v2は指示実行モデル、フルモデルです。 ", - "url": "https://huggingface.co/owner203/japanese-llama-3-8b-instruct-v2", - "project_name": "japanese-llama-3-8b-instruct-v2", - "downloads": 87, + "description": "Japanese ELECTRA-small We provide a Japanese ELECTRA-Small model, as described in ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators.", + "url": "https://huggingface.co/cinmodel/electra-small-japanese-generator", + "project_name": "electra-small-japanese-generator", + "downloads": 92, "source": "Hugging Face", - "score": -0.11307900944280287, - "first_commit": "2024-06-10 10:10:19", - "latest_commit": "2024-06-21 06:35:31", + "score": -0.0918193471269156, + "first_commit": "2020-11-13 06:49:52", + "latest_commit": "2020-12-11 22:26:17", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": "LlamaForCausalLM" + "model_size": null, + "model_architectures": "ElectraForMaskedLM" }, { - "description": "sonoisa/t5-base-japaneseをファインチューニングして、タイトル生成に用いれるようにしたモデルです。 ", - "url": "https://huggingface.co/Mizuiro-sakura/t5-CAMERA-title-generation", - "project_name": "t5-CAMERA-title-generation", - "downloads": 86, + "description": "[github].", + "url": "https://huggingface.co/datasets/fujiki/japanese_alpaca_data", + "project_name": "japanese_alpaca_data", + "downloads": 92, "source": "Hugging Face", - "score": -0.11309472079949709, - "first_commit": "2023-03-21 10:49:27", - "latest_commit": "2023-07-21 14:11:13", + "score": -0.0918193471269156, + "first_commit": "2023-05-18 07:13:15", + "latest_commit": "2023-05-19 12:54:13", "languages": [], - "model_or_dataset": "model", - "model_size": 0.223, - "model_architectures": "T5ForConditionalGeneration" + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null }, { - "description": "lightblue-Karasu-Mixtral-8x22B-v0.1-gguf lightblueさんが公開しているKarasu-Mixtral-8x22B-v0.1のggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/lightblue-Karasu-Mixtral-8x22B-v0.1-gguf", - "project_name": "lightblue-Karasu-Mixtral-8x22B-v0.1-gguf", - "downloads": 85, + "description": "Orion-14B 🌐English | 🇨", + "url": "https://huggingface.co/OrionStarAI/Orion-14B-Chat-Int4", + "project_name": "Orion-14B-Chat-Int4", + "downloads": 91, "source": "Hugging Face", - "score": -0.1131104321561913, - "first_commit": "2024-05-07 12:53:56", - "latest_commit": "2024-05-07 18:07:43", + "score": -0.09182995207745194, + "first_commit": "2024-01-18 09:54:07", + "latest_commit": "2024-03-26 10:04:46", "languages": [], "model_or_dataset": "model", - "model_size": 141.0, - "model_architectures": null + "model_size": 2.69, + "model_architectures": "OrionForCausalLM" }, { - "description": "Dataset 5M (5121625) clean Japanese full sentence with the context.", - "url": "https://huggingface.co/datasets/AhmedSSabir/Japanese-wiki-dump-sentence-dataset", - "project_name": "Japanese-wiki-dump-sentence-dataset", - "downloads": 83, + "description": "nlp-waseda/roberta-large-japanese Model description This is a Japanese RoBERTa large model pretrained on Japanese Wikipedia and the Japanese portion of CC-100.", + "url": "https://huggingface.co/nlp-waseda/roberta-large-japanese", + "project_name": "roberta-large-japanese", + "downloads": 91, "source": "Hugging Face", - "score": -0.11314185486957974, - "first_commit": "2022-06-08 11:34:04", - "latest_commit": "2023-07-11 12:22:09", - "languages": [], + "score": -0.09182995207745194, + "first_commit": "2022-05-10 08:37:48", + "latest_commit": "2022-10-21 14:48:46", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "RobertaForMaskedLM" + }, + { + "description": "Dataset Preprocessing Supported Tasks and Leaderboards Languages 注釈はすべて日本語を主要言語としています。 ", + "url": "https://huggingface.co/datasets/shunk031/jsnli", + "project_name": "jsnli", + "downloads": 89, + "source": "Hugging Face", + "score": -0.09185116197852461, + "first_commit": "2022-12-01 01:31:32", + "latest_commit": "2022-12-12 16:36:58", + "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "Aerner LM-v2 事前学習から全部日本語で学習させたモデルのバージョン2です。 ", - "url": "https://huggingface.co/aerner/lm-v2", - "project_name": "lm-v2", - "downloads": 82, + "description": "Ruri: Japanese General Text Embeddings Usage Direct Usage (Sentence Transformers)", + "url": "https://huggingface.co/cl-nagoya/ruri-base", + "project_name": "ruri-base", + "downloads": 87, "source": "Hugging Face", - "score": -0.11315756622627396, - "first_commit": "2023-06-09 15:19:12", - "latest_commit": "2023-06-09 16:08:47", + "score": -0.09187237187959726, + "first_commit": "2024-08-28 13:09:10", + "latest_commit": "2024-09-04 08:49:23", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "OpenLlamaForCausalLM" + "model_size": 0.111, + "model_architectures": "BertModel" + }, + { + "description": "lightblue-Karasu-Mixtral-8x22B-v0.1-gguf lightblueさんが公開しているKarasu-Mixtral-8x22B-v0.1のggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/lightblue-Karasu-Mixtral-8x22B-v0.1-gguf", + "project_name": "lightblue-Karasu-Mixtral-8x22B-v0.1-gguf", + "downloads": 86, + "source": "Hugging Face", + "score": -0.0918829768301336, + "first_commit": "2024-05-07 12:53:56", + "latest_commit": "2024-05-07 18:07:43", + "languages": [], + "model_or_dataset": "model", + "model_size": 141.0, + "model_architectures": null + }, + { + "description": "shisa-7b-v1-gguf augmxntさんが公開しているshisa-7b-v1のggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/shisa-7b-v1-gguf", + "project_name": "shisa-7b-v1-gguf", + "downloads": 85, + "source": "Hugging Face", + "score": -0.09189358178066993, + "first_commit": "2023-12-09 14:02:20", + "latest_commit": "2023-12-10 12:24:25", + "languages": [], + "model_or_dataset": "model", + "model_size": 7.96, + "model_architectures": null + }, + { + "description": "このモデルはluke-japanese-base-liteをファインチューニングして、Question-Answeringに用いれるようにしたものです。 ", + "url": "https://huggingface.co/Mizuiro-sakura/luke-japanese-base-finetuned-QA", + "project_name": "luke-japanese-base-finetuned-QA", + "downloads": 83, + "source": "Hugging Face", + "score": -0.0919147916817426, + "first_commit": "2023-01-15 23:38:30", + "latest_commit": "2023-07-21 14:11:02", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.132, + "model_architectures": "LukeForQuestionAnswering" }, { "description": "Llama 3 Youko 70B (rinna/llama-3-youko-70b)", "url": "https://huggingface.co/rinna/llama-3-youko-70b", "project_name": "llama-3-youko-70b", - "downloads": 81, + "downloads": 83, "source": "Hugging Face", - "score": -0.11317327758296818, + "score": -0.0919147916817426, "first_commit": "2024-07-21 14:13:34", "latest_commit": "2024-07-25 05:16:28", "languages": [], @@ -9092,40 +9025,82 @@ "model_architectures": "LlamaForCausalLM" }, { - "description": "We provide an Amazon product reviews dataset for multilingual text classification.", - "url": "https://huggingface.co/datasets/defunct-datasets/amazon_reviews_multi", - "project_name": "amazon_reviews_multi", - "downloads": 80, + "description": "AIBunCho/japanese-novel-gpt-j-6b AI BunChoで利用しているモデルです。", + "url": "https://huggingface.co/AIBunCho/japanese-novel-gpt-j-6b", + "project_name": "japanese-novel-gpt-j-6b", + "downloads": 82, "source": "Hugging Face", - "score": -0.1131889889396624, - "first_commit": "2022-01-25 16:34:54", - "latest_commit": "2023-11-02 14:52:21", + "score": -0.09192539663227894, + "first_commit": "2023-08-11 00:52:32", + "latest_commit": "2023-08-26 04:20:51", "languages": [], - "model_or_dataset": "dataset", + "model_or_dataset": "model", "model_size": null, + "model_architectures": "GPTJForCausalLM" + }, + { + "description": "Model card for model ID", + "url": "https://huggingface.co/retrieva-jp/t5-large-medium", + "project_name": "t5-large-medium", + "downloads": 81, + "source": "Hugging Face", + "score": -0.09193600158281527, + "first_commit": "2023-04-26 08:31:45", + "latest_commit": "2023-05-10 10:00:45", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "T5ForConditionalGeneration" + }, + { + "description": "line-corporation/japanese-large-lm-3.6b-instruction-sft line-corporationさんが公開しているjapanese-large-lm-3.6b-instruction-sftのgguf変換版です。 ", + "url": "https://huggingface.co/mmnga/line-corp-japanese-large-lm-3.6b-instruction-sft-gguf", + "project_name": "line-corp-japanese-large-lm-3.6b-instruction-sft-gguf", + "downloads": 80, + "source": "Hugging Face", + "score": -0.09194660653335161, + "first_commit": "2023-09-02 18:01:40", + "latest_commit": "2023-09-08 02:52:29", + "languages": [], + "model_or_dataset": "model", + "model_size": 3.71, "model_architectures": null }, { - "description": "Japanese InstructBLIP Alpha Model Details Japanese InstructBLIP Alpha is a vision-language instruction-following model that enables to generate Japanese descriptions for input images and optionally input texts such as questions.", - "url": "https://huggingface.co/stabilityai/japanese-instructblip-alpha", - "project_name": "japanese-instructblip-alpha", + "description": "roberta_qa_japanese (Japanese caption : 日本語の (抽出型) 質問応答のモデル)", + "url": "https://huggingface.co/tsmatz/roberta_qa_japanese", + "project_name": "roberta_qa_japanese", + "downloads": 80, + "source": "Hugging Face", + "score": -0.09194660653335161, + "first_commit": "2022-12-11 03:41:07", + "latest_commit": "2024-07-12 00:00:07", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.11, + "model_architectures": "RobertaForQuestionAnswering" + }, + { + "description": "reazonspeech-espnet-next ReazonSpeech is a project to maintain freely-available Japanese audio datasets and ML models.", + "url": "https://huggingface.co/reazon-research/reazonspeech-espnet-next", + "project_name": "reazonspeech-espnet-next", "downloads": 79, "source": "Hugging Face", - "score": -0.11320470029635661, - "first_commit": "2023-08-16 23:49:58", - "latest_commit": "2023-11-17 03:57:41", + "score": -0.09195721148388794, + "first_commit": "2023-03-29 07:20:03", + "latest_commit": "2023-03-29 17:28:01", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "JapaneseInstructBlipAlphaForConditionalGeneration" + "model_architectures": null }, { "description": "HODACHI様の Llama-3-EZO-8b-Common-it をGGUF形式に変換したものです。 ", "url": "https://huggingface.co/MCZK/Llama-3-EZO-8b-Common-it-GGUF", "project_name": "Llama-3-EZO-8b-Common-it-GGUF", - "downloads": 78, + "downloads": 79, "source": "Hugging Face", - "score": -0.11322041165305083, + "score": -0.09195721148388794, "first_commit": "2024-07-15 11:58:12", "latest_commit": "2024-07-15 20:08:22", "languages": [], @@ -9134,54 +9109,68 @@ "model_architectures": null }, { - "description": "Anime with caption CC-0 dataset このデータセットはイラストに対する日本語キャプションを 倫理的に学習しやすくするためのデータセットです。 ", - "url": "https://huggingface.co/datasets/alfredplpl/anime-with-caption-cc0", - "project_name": "anime-with-caption-cc0", - "downloads": 77, + "description": "Local-Novel-LLM-project様の Ninja-V3 をGGUF形式に変換したものです。 ", + "url": "https://huggingface.co/MCZK/Ninja-V3-GGUF", + "project_name": "Ninja-V3-GGUF", + "downloads": 79, "source": "Hugging Face", - "score": -0.11323612300974505, - "first_commit": "2024-06-03 04:37:13", - "latest_commit": "2024-06-03 05:49:20", + "score": -0.09195721148388794, + "first_commit": "2024-07-03 11:52:04", + "latest_commit": "2024-07-03 16:59:05", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_or_dataset": "model", + "model_size": 7.24, "model_architectures": null }, { - "description": "このデータセットについて このデータは、日本の官公庁のWebサイトに掲載されている「よくある質問」を手作業で抽出し、インストラクション用のデータセットとしたものです。 ", - "url": "https://huggingface.co/datasets/matsuxr/JaGovFaqs-22k", - "project_name": "JaGovFaqs-22k", - "downloads": 76, + "description": "Asian Language Treebank (ALT) Project ALT Parallel Corpusのうち、日英対訳部分のみを抽出したデータセットです。", + "url": "https://huggingface.co/datasets/hpprc/alt-parallel-en-ja", + "project_name": "alt-parallel-en-ja", + "downloads": 79, "source": "Hugging Face", - "score": -0.11325183436643926, - "first_commit": "2023-12-31 13:58:41", - "latest_commit": "2024-02-29 02:51:20", + "score": -0.09195721148388794, + "first_commit": "2024-03-21 02:24:27", + "latest_commit": "2024-03-21 12:40:15", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "Model card for model ID", - "url": "https://huggingface.co/retrieva-jp/t5-small-medium", - "project_name": "t5-small-medium", - "downloads": 75, + "description": "Japanese ELECTRA-small We provide a Japanese ELECTRA-Small model, as described in ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators.", + "url": "https://huggingface.co/cinmodel/electra-small-japanese-discriminator", + "project_name": "electra-small-japanese-discriminator", + "downloads": 77, "source": "Hugging Face", - "score": -0.11326754572313348, - "first_commit": "2023-04-26 08:26:19", - "latest_commit": "2023-05-10 10:01:16", + "score": -0.09197842138496061, + "first_commit": "2020-11-13 06:49:25", + "latest_commit": "2020-12-11 22:26:13", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "T5ForConditionalGeneration" + "model_architectures": "ElectraForPreTraining" + }, + { + "description": "COMET-GPT2 ja Finetuned GPT-2 on ATOMIC ja using a causal language modeling (CLM) objective.", + "url": "https://huggingface.co/nlp-waseda/comet-gpt2-small-japanese", + "project_name": "comet-gpt2-small-japanese", + "downloads": 77, + "source": "Hugging Face", + "score": -0.09197842138496061, + "first_commit": "2022-11-15 05:14:35", + "latest_commit": "2023-02-13 10:26:12", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "GPT2LMHeadModel" }, { "description": "モデルの説明(English explanation is below.", "url": "https://huggingface.co/keitokei1994/swallow-3-8B-sqlcoder-2x8B-GGUF", "project_name": "swallow-3-8B-sqlcoder-2x8B-GGUF", - "downloads": 75, + "downloads": 77, "source": "Hugging Face", - "score": -0.11326754572313348, + "score": -0.09197842138496061, "first_commit": "2024-07-03 11:02:45", "latest_commit": "2024-07-04 07:20:41", "languages": [], @@ -9190,110 +9179,348 @@ "model_architectures": null }, { - "description": "Wikipediaを用いた日本語の固有表現抽出データセット GitHub: https://github.com/stockmarkteam/ner-wikipedia-dataset/ LICENSE: CC-BY-SA 3.0 Developed by Stockmark Inc.", - "url": "https://huggingface.co/datasets/stockmark/ner-wikipedia-dataset", - "project_name": "ner-wikipedia-dataset", + "description": "Original Model Optical character recognition for Japanese text, with the main focus being Japanese manga.", + "url": "https://huggingface.co/TareHimself/manga-ocr-base", + "project_name": "manga-ocr-base", + "downloads": 77, + "source": "Hugging Face", + "score": -0.09197842138496061, + "first_commit": "2023-09-14 04:15:52", + "latest_commit": "2024-06-03 05:10:11", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.111, + "model_architectures": "VisionEncoderDecoderModel" + }, + { + "description": "Dataset 5M (5121625) clean Japanese full sentence with the context.", + "url": "https://huggingface.co/datasets/AhmedSSabir/Japanese-wiki-dump-sentence-dataset", + "project_name": "Japanese-wiki-dump-sentence-dataset", + "downloads": 77, + "source": "Hugging Face", + "score": -0.09197842138496061, + "first_commit": "2022-06-08 11:34:04", + "latest_commit": "2023-07-11 12:22:09", + "languages": [], + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null + }, + { + "description": "ChatNTQ JA 7B V1.0 Model Description", + "url": "https://huggingface.co/NTQAI/chatntq-ja-7b-v1.0", + "project_name": "chatntq-ja-7b-v1.0", + "downloads": 76, + "source": "Hugging Face", + "score": -0.09198902633549694, + "first_commit": "2023-12-26 06:22:59", + "latest_commit": "2023-12-26 09:22:34", + "languages": [], + "model_or_dataset": "model", + "model_size": 7.24, + "model_architectures": "MistralForCausalLM" + }, + { + "description": "Llama-3-8B-Instruct-JP-nk2t-v0.2 Model Details: Built with Meta Llama 3", + "url": "https://huggingface.co/nk2t/Llama-3-8B-Instruct-japanese-nk2t-v0.2", + "project_name": "Llama-3-8B-Instruct-japanese-nk2t-v0.2", + "downloads": 72, + "source": "Hugging Face", + "score": -0.09203144613764228, + "first_commit": "2024-05-04 04:16:35", + "latest_commit": "2024-05-15 12:56:34", + "languages": [], + "model_or_dataset": "model", + "model_size": 8.03, + "model_architectures": "LlamaForCausalLM" + }, + { + "description": "fio-base-japanese-v0.1 日本語版は近日公開予定です（日本語を勉強中なので、間違いはご容赦ください！", + "url": "https://huggingface.co/bclavie/fio-base-japanese-v0.1", + "project_name": "fio-base-japanese-v0.1", + "downloads": 72, + "source": "Hugging Face", + "score": -0.09203144613764228, + "first_commit": "2023-12-18 11:01:07", + "latest_commit": "2023-12-19 10:28:16", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.111, + "model_architectures": "BertModel" + }, + { + "description": "Sakura_dataset 商用利用可能な超小規模高品質日本語データセット。 ", + "url": "https://huggingface.co/datasets/saldra/sakura_japanese_dataset", + "project_name": "sakura_japanese_dataset", "downloads": 72, "source": "Hugging Face", - "score": -0.11331467979321613, - "first_commit": "2023-09-02 14:38:55", - "latest_commit": "2023-09-02 14:42:18", + "score": -0.09203144613764228, + "first_commit": "2023-06-07 05:44:23", + "latest_commit": "2023-06-08 11:31:06", + "languages": [], + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null + }, + { + "description": "range3/cc100-ja This dataset consists of parquet files from the cc100 dataset with only the Japanese language extracted and sharded.", + "url": "https://huggingface.co/datasets/range3/cc100-ja", + "project_name": "cc100-ja", + "downloads": 70, + "source": "Hugging Face", + "score": -0.09205265603871494, + "first_commit": "2023-02-04 05:10:34", + "latest_commit": "2023-02-04 05:43:32", + "languages": [], + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null + }, + { + "description": "モデル概要 このモデルは、 sonoisa/sentence-luke-japanese-base-lite をSNS上のコメントに人手で攻撃性評価を行ったデータセットでFine-tuningすることで作成しました。 ", + "url": "https://huggingface.co/TomokiFujihara/luke-japanese-base-lite-offensiveness-estimation", + "project_name": "luke-japanese-base-lite-offensiveness-estimation", + "downloads": 69, + "source": "Hugging Face", + "score": -0.09206326098925129, + "first_commit": "2023-12-08 03:20:14", + "latest_commit": "2024-03-24 12:35:36", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.133, + "model_architectures": "OffensivenessEstimationModel" + }, + { + "description": "Finetuned Waseda RoBERTa to evaluate the generated answers on JTruthfulQA.", + "url": "https://huggingface.co/nlp-waseda/roberta_jtruthfulqa", + "project_name": "roberta_jtruthfulqa", + "downloads": 69, + "source": "Hugging Face", + "score": -0.09206326098925129, + "first_commit": "2023-12-06 01:33:02", + "latest_commit": "2023-12-06 04:31:12", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.337, + "model_architectures": "RobertaForSequenceClassification" + }, + { + "description": "llm-book/bert-base-japanese-v3-crf-ner-wikipedia-dataset 「大規模言語モデル入門」の第6章で紹介している固有表現認識のモデルです。 ", + "url": "https://huggingface.co/llm-book/bert-base-japanese-v3-crf-ner-wikipedia-dataset", + "project_name": "bert-base-japanese-v3-crf-ner-wikipedia-dataset", + "downloads": 68, + "source": "Hugging Face", + "score": -0.09207386593978761, + "first_commit": "2023-05-28 08:19:43", + "latest_commit": "2023-07-25 15:04:39", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "BertWithCrfForTokenClassification" + }, + { + "description": "Vecteus-V2-7B このモデルは、ベクトルマージなどを用い作成された高性能ベースモデルです。 ", + "url": "https://huggingface.co/Local-Novel-LLM-project/Vecteus-V2-7B", + "project_name": "Vecteus-V2-7B", + "downloads": 68, + "source": "Hugging Face", + "score": -0.09207386593978761, + "first_commit": "2024-06-16 03:51:43", + "latest_commit": "2024-07-06 13:39:41", + "languages": [], + "model_or_dataset": "model", + "model_size": 7.24, + "model_architectures": "MistralForCausalLM" + }, + { + "description": "https://huggingface.co/kotoba-tech/kotoba-whisper-v1.1 上記のモデルを訓練し、アダルト用語を認識できるようにしたものです���", + "url": "https://huggingface.co/swdq/Visual-novel-whisper", + "project_name": "Visual-novel-whisper", + "downloads": 67, + "source": "Hugging Face", + "score": -0.09208447089032394, + "first_commit": "2024-07-24 10:09:29", + "latest_commit": "2024-07-24 10:29:47", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.756, + "model_architectures": "WhisperForConditionalGeneration" + }, + { + "description": "This is for (private) DEMO only.", + "url": "https://huggingface.co/Bagus/wav2vec2-xlsr-japanese-speech-emotion-recognition", + "project_name": "wav2vec2-xlsr-japanese-speech-emotion-recognition", + "downloads": 66, + "source": "Hugging Face", + "score": -0.09209507584086028, + "first_commit": "2021-09-22 04:10:36", + "latest_commit": "2023-10-19 01:31:17", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.316, + "model_architectures": "HubertForSequenceClassification" + }, + { + "description": "llm-lora-classification", + "url": "https://github.com/hppRC/llm-lora-classification", + "project_name": "llm-lora-classification", + "stargazers_count": 83, + "source": "GitHub", + "score": -0.09209518952964318, + "first_commit": "2023-07-17 12:42:57", + "latest_commit": "2023-07-22 19:46:45", + "languages": [ + "Python" + ], + "model_or_dataset": null + }, + { + "description": "Word2vec (word to vectors) approach for Japanese language using Gensim and Mecab.", + "url": "https://github.com/philipperemy/japanese-words-to-vectors", + "project_name": "japanese-words-to-vectors", + "stargazers_count": 83, + "source": "GitHub", + "score": -0.09209518952964318, + "first_commit": "2016-09-04 09:43:00", + "latest_commit": "2020-08-09 19:48:23", + "languages": [ + "Python" + ], + "model_or_dataset": "model" + }, + { + "description": "BERT base Japanese - JaQuAD Description A Japanese Question Answering model fine-tuned on JaQuAD.", + "url": "https://huggingface.co/SkelterLabsInc/bert-base-japanese-jaquad", + "project_name": "bert-base-japanese-jaquad", + "downloads": 65, + "source": "Hugging Face", + "score": -0.09210568079139661, + "first_commit": "2022-01-27 08:08:53", + "latest_commit": "2022-02-04 02:39:25", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "BertForQuestionAnswering" + }, + { + "description": "SakuraMixSeries 背景とキャラクタークオリティーを両立させたVAE内蔵型モデル Model with built-in VAE for both background and character quality 📄 ライセンス / License 修正 CreativeML OpenRAIL-M ライセンス / Modified CreativeML OpenRAIL-M license このモデルのクレジットを入れずに使用する Use the model without crediting the creator このモデルで生成した画像を商用利用する Sell images they generate このモデルを商用の画像生成サービスで利用する Run on services that generate images for money このモデルを使用したマージモデルを共有する Share merges using this model このモデル、またはこのモデルをマージしたモデルを販売する Sell this model or merges using this model このモデ", + "url": "https://huggingface.co/natsusakiyomi/SakuraMix", + "project_name": "SakuraMix", + "downloads": 65, + "source": "Hugging Face", + "score": -0.09210568079139661, + "first_commit": "2023-03-17 17:37:21", + "latest_commit": "2023-08-22 12:30:44", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": null + }, + { + "description": "HODACHI様の EZO-Common-T2-2B-gemma-2-it をGGUF形式に変換したものです。 ", + "url": "https://huggingface.co/MCZK/EZO-Common-T2-2B-gemma-2-it-GGUF", + "project_name": "EZO-Common-T2-2B-gemma-2-it-GGUF", + "downloads": 65, + "source": "Hugging Face", + "score": -0.09210568079139661, + "first_commit": "2024-08-01 11:38:48", + "latest_commit": "2024-08-01 13:42:20", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_or_dataset": "model", + "model_size": 2.61, "model_architectures": null }, { - "description": "Model card for model ID", - "url": "https://huggingface.co/retrieva-jp/t5-base-medium", - "project_name": "t5-base-medium", - "downloads": 71, + "description": "line-corporation/japanese-large-lm-1.7b line-corporationさんが公開しているjapanese-large-lm-1.7bのgguf変換版です。 ", + "url": "https://huggingface.co/mmnga/line-corp-japanese-large-lm-1.7b-gguf", + "project_name": "line-corp-japanese-large-lm-1.7b-gguf", + "downloads": 65, "source": "Hugging Face", - "score": -0.11333039114991034, - "first_commit": "2023-04-26 08:27:09", - "latest_commit": "2023-05-10 10:00:12", + "score": -0.09210568079139661, + "first_commit": "2023-09-03 22:35:34", + "latest_commit": "2024-03-24 05:54:30", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "T5ForConditionalGeneration" + "model_size": 1.77, + "model_architectures": null }, { - "description": "range3/cc100-ja This dataset consists of parquet files from the cc100 dataset with only the Japanese language extracted and sharded.", - "url": "https://huggingface.co/datasets/range3/cc100-ja", - "project_name": "cc100-ja", - "downloads": 69, + "description": "Deepreneur-blue-lizard-gguf Deepreneurさんが公開しているblue-lizardのggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Deepreneur-blue-lizard-gguf", + "project_name": "Deepreneur-blue-lizard-gguf", + "downloads": 63, "source": "Hugging Face", - "score": -0.11336181386329877, - "first_commit": "2023-02-04 05:10:34", - "latest_commit": "2023-02-04 05:43:32", + "score": -0.09212689069246928, + "first_commit": "2024-02-13 15:18:15", + "latest_commit": "2024-02-13 16:26:26", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_or_dataset": "model", + "model_size": 6.74, "model_architectures": null }, { - "description": "roberta-long-japanese (jumanpp + sentencepiece, mC4 Japanese)", - "url": "https://huggingface.co/megagonlabs/roberta-long-japanese", - "project_name": "roberta-long-japanese", - "downloads": 67, + "description": "Ruri: Japanese General Text Embeddings Usage Direct Usage (Sentence Transformers)", + "url": "https://huggingface.co/cl-nagoya/ruri-small", + "project_name": "ruri-small", + "downloads": 62, "source": "Hugging Face", - "score": -0.1133932365766872, - "first_commit": "2022-09-04 14:31:06", - "latest_commit": "2022-10-04 23:36:27", + "score": -0.09213749564300562, + "first_commit": "2024-08-28 16:23:12", + "latest_commit": "2024-09-04 08:49:30", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "RobertaForMaskedLM" + "model_size": 0.0681, + "model_architectures": "DistilBertModel" }, { - "description": "モデル概要 このモデルは、 sonoisa/sentence-luke-japanese-base-lite をSNS上のコメントに人手で攻撃性評価を行ったデータセットでFine-tuningすることで作成しました。 ", - "url": "https://huggingface.co/TomokiFujihara/luke-japanese-base-lite-offensiveness-estimation", - "project_name": "luke-japanese-base-lite-offensiveness-estimation", - "downloads": 66, + "description": "Wav2Vec2-Large-XLSR-53-Japanese Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using the Common Voice and Japanese speech corpus of Saruwatari-lab, University of Tokyo JSUT.", + "url": "https://huggingface.co/vumichien/wav2vec2-large-xlsr-japanese", + "project_name": "wav2vec2-large-xlsr-japanese", + "downloads": 62, "source": "Hugging Face", - "score": -0.11340894793338142, - "first_commit": "2023-12-08 03:20:14", - "latest_commit": "2024-03-24 12:35:36", + "score": -0.09213749564300562, + "first_commit": "2021-03-28 04:21:20", + "latest_commit": "2023-02-08 00:15:23", "languages": [], "model_or_dataset": "model", - "model_size": 0.133, - "model_architectures": "OffensivenessEstimationModel" + "model_size": 0.318, + "model_architectures": "Wav2Vec2ForCTC" }, { - "description": "albert-base-japanese-v1-with-japanese 日本語事前学習済みALBERTモデルですこのモデルではTokenizerにBertJapaneseTokenizerクラスを利用していますalbert-base-japanese-v1よりトークナイズ処理が楽になっています How to use ファインチューニング このモデルはPreTrainedモデルです基本的には各種タスク用にファインチューニングして使用されることを想定しています Fill-Mask for PyTorch from transformers import ( AutoModelForMaskedLM, AutoTokenizer ) tokenizer = AutoTokenizer.from_pretrained(\"ken11/albert-base-japanese-v1-with-japanese-tokenizer\")", - "url": "https://huggingface.co/ken11/albert-base-japanese-v1-with-japanese-tokenizer", - "project_name": "albert-base-japanese-v1-with-japanese-tokenizer", - "downloads": 65, + "description": "Kanji Diffusion v1-4 Model Card Kanji Diffusion is a latent text-to-image diffusion model capable of hallucinating Kanji characters given any English prompt.", + "url": "https://huggingface.co/yashvoladoddi37/kanji-diffusion-v1-4", + "project_name": "kanji-diffusion-v1-4", + "downloads": 62, "source": "Hugging Face", - "score": -0.11342465929007564, - "first_commit": "2022-04-20 16:34:22", - "latest_commit": "2022-04-21 02:28:13", + "score": -0.09213749564300562, + "first_commit": "2024-08-13 06:06:21", + "latest_commit": "2024-08-16 12:14:22", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "AlbertForMaskedLM" + "model_architectures": null }, { - "description": "Umievo-itr012-Gleipnir-7B このモデルは強力な４つの日本語モデルを進化的アルゴリズムで進化的マージしたものです。", - "url": "https://huggingface.co/umiyuki/Umievo-itr012-Gleipnir-7B", - "project_name": "Umievo-itr012-Gleipnir-7B", - "downloads": 65, + "description": "shisa-v1-qwen2-7b-gguf (English explanation is below.", + "url": "https://huggingface.co/keitokei1994/shisa-v1-qwen2-7b-GGUF", + "project_name": "shisa-v1-qwen2-7b-GGUF", + "downloads": 62, "source": "Hugging Face", - "score": -0.11342465929007564, - "first_commit": "2024-05-29 12:32:29", - "latest_commit": "2024-05-29 13:51:31", + "score": -0.09213749564300562, + "first_commit": "2024-06-09 08:58:45", + "latest_commit": "2024-07-04 07:44:00", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": "MistralForCausalLM" + "model_size": 7.62, + "model_architectures": null }, { "description": "c4ai-command-r-v01-japanese-instruct GGUF版はこちら/Click here for the GGUF version 概要 CohereForAI/c4ai-command-r-v01を、ichikara-instructionを使って追加で日本語インストラクションチューニングを施したモデルです。 ", "url": "https://huggingface.co/Aratako/c4ai-command-r-v01-japanese-instruct", "project_name": "c4ai-command-r-v01-japanese-instruct", - "downloads": 64, + "downloads": 62, "source": "Hugging Face", - "score": -0.11344037064676986, + "score": -0.09213749564300562, "first_commit": "2024-04-04 03:56:52", "latest_commit": "2024-04-07 15:18:37", "languages": [], @@ -9302,124 +9529,152 @@ "model_architectures": "CohereForCausalLM" }, { - "description": "https://huggingface.co/kotoba-tech/kotoba-whisper-v1.1 上記のモデルを訓練し、アダルト用語を認識できるようにしたものです。", - "url": "https://huggingface.co/swdq/Visual-novel-whisper", - "project_name": "Visual-novel-whisper", - "downloads": 63, + "description": "275.86Mのmixtralを日本語データセットでpretrainingしたものです sample from transformers import AutoTokenizer, AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained(\"if001/tiny_mixtral_ja\")", + "url": "https://huggingface.co/if001/tiny_mixtral_ja", + "project_name": "tiny_mixtral_ja", + "downloads": 61, "source": "Hugging Face", - "score": -0.11345608200346408, - "first_commit": "2024-07-24 10:09:29", - "latest_commit": "2024-07-24 10:29:47", + "score": -0.09214810059354195, + "first_commit": "2024-01-22 15:02:21", + "latest_commit": "2024-01-23 00:42:05", "languages": [], "model_or_dataset": "model", - "model_size": 0.756, - "model_architectures": "WhisperForConditionalGeneration" + "model_size": 0.276, + "model_architectures": "MixtralForCausalLM" }, { - "description": "このモデルはluke-japanese-base-liteをファインチューニングして、Question-Answeringに用いれるようにしたものです。 ", - "url": "https://huggingface.co/Mizuiro-sakura/luke-japanese-base-finetuned-QA", - "project_name": "luke-japanese-base-finetuned-QA", - "downloads": 63, + "description": "Google's mt5-base fine-tuned in Japanese to solve error detection and correction task. ", + "url": "https://huggingface.co/kz/mt5base-finetuned-ECC-japanese-small", + "project_name": "mt5base-finetuned-ECC-japanese-small", + "downloads": 61, "source": "Hugging Face", - "score": -0.11345608200346408, - "first_commit": "2023-01-15 23:38:30", - "latest_commit": "2023-07-21 14:11:02", + "score": -0.09214810059354195, + "first_commit": "2021-03-21 19:07:13", + "latest_commit": "2022-05-26 13:50:56", "languages": [], "model_or_dataset": "model", - "model_size": 0.132, - "model_architectures": "LukeForQuestionAnswering" + "model_size": null, + "model_architectures": "MT5ForConditionalGeneration" }, { - "description": "Asian Language Treebank (ALT) Project ALT Parallel Corpusのうち、日英対訳部分のみを抽出したデータセットです。", - "url": "https://huggingface.co/datasets/hpprc/alt-parallel-en-ja", - "project_name": "alt-parallel-en-ja", - "downloads": 63, + "description": "japanese-large-lm-3.6b-instruction-sft-8bit-1g-actorder_True", + "url": "https://huggingface.co/line-corporation/japanese-large-lm-3.6b-instruction-sft-8bit-1g-actorder_True", + "project_name": "japanese-large-lm-3.6b-instruction-sft-8bit-1g-actorder_True", + "downloads": 61, "source": "Hugging Face", - "score": -0.11345608200346408, - "first_commit": "2024-03-21 02:24:27", - "latest_commit": "2024-03-21 12:40:15", + "score": -0.09214810059354195, + "first_commit": "2023-09-26 06:16:23", + "latest_commit": "2023-09-28 00:02:06", + "languages": [], + "model_or_dataset": "model", + "model_size": 1.17, + "model_architectures": "GPTNeoXForCausalLM" + }, + { + "description": "概要 NHKで定期的に放送されていた『着信御礼！", + "url": "https://huggingface.co/datasets/YANS-official/ogiri-keitai", + "project_name": "ogiri-keitai", + "downloads": 59, + "source": "Hugging Face", + "score": -0.09216931049461462, + "first_commit": "2024-07-20 10:11:36", + "latest_commit": "2024-08-30 10:13:20", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "Synthetic-Japanese-Roleplay-gpt-4o-mini-19.8k 概要 gpt-4o-miniを用いて作成した、約19800件の日本語ロールプレイの対話を収録した合成データセットです。", - "url": "https://huggingface.co/datasets/Aratako/Synthetic-Japanese-Roleplay-gpt-4o-mini-19.8k", - "project_name": "Synthetic-Japanese-Roleplay-gpt-4o-mini-19.8k", - "downloads": 63, + "description": "Model card for model ID", + "url": "https://huggingface.co/retrieva-jp/t5-small-medium", + "project_name": "t5-small-medium", + "downloads": 58, "source": "Hugging Face", - "score": -0.11345608200346408, - "first_commit": "2024-08-16 14:35:16", - "latest_commit": "2024-08-16 16:45:26", + "score": -0.09217991544515095, + "first_commit": "2023-04-26 08:26:19", + "latest_commit": "2023-05-10 10:01:16", "languages": [], - "model_or_dataset": "dataset", + "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "T5ForConditionalGeneration" }, { - "description": "GGUF conversion of NTQAI/chatntq-ja-7b-v1.0 ChatNTQ-JA-7b-v1.0 is a Japanese chat fine-tuned model built on top of the stabilityai/japanese-stablelm-base-gamma-7b, which is originally based on Mistral 7B v0.1.", - "url": "https://huggingface.co/TFMC/ChatNTQ-JA-7b-v1.0-GGUF", - "project_name": "ChatNTQ-JA-7b-v1.0-GGUF", - "downloads": 62, + "description": "Umievo-itr012-Gleipnir-7B このモデルは強力な４つの日本語モデルを進化的アルゴリズムで進化的マージしたものです。", + "url": "https://huggingface.co/umiyuki/Umievo-itr012-Gleipnir-7B", + "project_name": "Umievo-itr012-Gleipnir-7B", + "downloads": 58, "source": "Hugging Face", - "score": -0.1134717933601583, - "first_commit": "2024-04-03 22:42:14", - "latest_commit": "2024-04-04 23:10:54", + "score": -0.09217991544515095, + "first_commit": "2024-05-29 12:32:29", + "latest_commit": "2024-05-29 13:51:31", "languages": [], "model_or_dataset": "model", "model_size": 7.24, + "model_architectures": "MistralForCausalLM" + }, + { + "description": "このデータセットはkunishou氏が公開している\"databricks-dolly-15k\"を日本語訳したkunishou/databricks-dolly-15k-jaデータセットの語尾をArrowPro-7B-KUJIRAを用いて「にゃん！", + "url": "https://huggingface.co/datasets/DataPilot/databricks-dolly-15k-Nyan-ja", + "project_name": "databricks-dolly-15k-Nyan-ja", + "downloads": 57, + "source": "Hugging Face", + "score": -0.09219052039568729, + "first_commit": "2024-05-18 13:03:25", + "latest_commit": "2024-05-19 10:24:16", + "languages": [], + "model_or_dataset": "dataset", + "model_size": null, "model_architectures": null }, { - "description": "Model card for model ID", - "url": "https://huggingface.co/retrieva-jp/t5-xl", - "project_name": "t5-xl", - "downloads": 62, + "description": "Dataset overview This dataset identifies whether a GitHub repository description pertains to Japanese natural language processing (NLP).", + "url": "https://huggingface.co/datasets/taishi-i/awesome-japanese-nlp-classification-dataset", + "project_name": "awesome-japanese-nlp-classification-dataset", + "downloads": 57, "source": "Hugging Face", - "score": -0.1134717933601583, - "first_commit": "2023-04-26 07:19:08", - "latest_commit": "2023-05-10 10:01:04", + "score": -0.09219052039568729, + "first_commit": "2023-09-09 06:37:36", + "latest_commit": "2023-09-09 20:09:04", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "T5ForConditionalGeneration" + "model_architectures": null }, { - "description": "Wav2Vec2-Large-XLSR-53-Japanese Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using the Common Voice and Japanese speech corpus of Saruwatari-lab, University of Tokyo JSUT.", - "url": "https://huggingface.co/vumichien/wav2vec2-large-xlsr-japanese", - "project_name": "wav2vec2-large-xlsr-japanese", - "downloads": 61, + "description": "英語+日本語T5事前学習済みモデル This is a T5 (Text-to-Text Transfer Transformer) model pretrained on English and Japanese balanced corpus. ", + "url": "https://huggingface.co/sonoisa/t5-base-english-japanese", + "project_name": "t5-base-english-japanese", + "downloads": 56, "source": "Hugging Face", - "score": -0.11348750471685251, - "first_commit": "2021-03-28 04:21:20", - "latest_commit": "2023-02-08 00:15:23", + "score": -0.09220112534622361, + "first_commit": "2022-07-28 11:31:28", + "latest_commit": "2022-08-27 09:07:53", "languages": [], "model_or_dataset": "model", - "model_size": 0.318, - "model_architectures": "Wav2Vec2ForCTC" + "model_size": null, + "model_architectures": "T5ForConditionalGeneration" }, { - "description": "ChatNTQ JA 7B V1.0 Model Description", - "url": "https://huggingface.co/NTQAI/chatntq-ja-7b-v1.0", - "project_name": "chatntq-ja-7b-v1.0", - "downloads": 60, + "description": "Heron BLIP Japanese StableLM", + "url": "https://huggingface.co/turing-motors/heron-chat-blip-ja-stablelm-base-7b-v1", + "project_name": "heron-chat-blip-ja-stablelm-base-7b-v1", + "downloads": 56, "source": "Hugging Face", - "score": -0.11350321607354673, - "first_commit": "2023-12-26 06:22:59", - "latest_commit": "2023-12-26 09:22:34", + "score": -0.09220112534622361, + "first_commit": "2024-02-20 11:32:57", + "latest_commit": "2024-02-27 13:57:20", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": "MistralForCausalLM" + "model_size": null, + "model_architectures": "VideoBlipForConditionalGeneration" }, { "description": "Orion-14B 🌐English | 🇨", "url": "https://huggingface.co/nold/Orion-14B-Base-GGUF", "project_name": "Orion-14B-Base-GGUF", - "downloads": 60, + "downloads": 55, "source": "Hugging Face", - "score": -0.11350321607354673, + "score": -0.09221173029675996, "first_commit": "2024-03-07 14:56:51", "latest_commit": "2024-03-07 19:33:53", "languages": [], @@ -9428,82 +9683,96 @@ "model_architectures": null }, { - "description": "Kanji Diffusion v1-4 Model Card Kanji Diffusion is a latent text-to-image diffusion model capable of hallucinating Kanji characters given any English prompt.", - "url": "https://huggingface.co/yashvoladoddi37/kanji-diffusion-v1-4", - "project_name": "kanji-diffusion-v1-4", - "downloads": 60, + "description": "studio-ousia/luke-japanese-baseに対して次の変更を加えたモデルです。 ", + "url": "https://huggingface.co/uzabase/luke-japanese-wordpiece-base", + "project_name": "luke-japanese-wordpiece-base", + "downloads": 55, "source": "Hugging Face", - "score": -0.11350321607354673, - "first_commit": "2024-08-13 06:06:21", - "latest_commit": "2024-08-16 12:14:22", + "score": -0.09221173029675996, + "first_commit": "2023-08-10 06:04:58", + "latest_commit": "2023-11-28 13:35:07", "languages": [], "model_or_dataset": "model", "model_size": null, + "model_architectures": "LukeForMaskedLM" + }, + { + "description": "GGUF conversion of NTQAI/chatntq-ja-7b-v1.0 ChatNTQ-JA-7b-v1.0 is a Japanese chat fine-tuned model built on top of the stabilityai/japanese-stablelm-base-gamma-7b, which is originally based on Mistral 7B v0.1.", + "url": "https://huggingface.co/TFMC/ChatNTQ-JA-7b-v1.0-GGUF", + "project_name": "ChatNTQ-JA-7b-v1.0-GGUF", + "downloads": 54, + "source": "Hugging Face", + "score": -0.09222233524729628, + "first_commit": "2024-04-03 22:42:14", + "latest_commit": "2024-04-04 23:10:54", + "languages": [], + "model_or_dataset": "model", + "model_size": 7.24, "model_architectures": null }, { - "description": "Cross-Encoder for Natural Language Inference(NLI) for Japanese Considering the results of the JNLI evaluation result, we recommend using akiFQC/bert-base-japanese-v3_nli-jsnli-jnli-jsick for natural language inference in Japanese.", - "url": "https://huggingface.co/akiFQC/bert-base-japanese-v3_nli-jsnli", - "project_name": "bert-base-japanese-v3_nli-jsnli", - "downloads": 59, + "description": "Model card for model ID", + "url": "https://huggingface.co/retrieva-jp/t5-xl", + "project_name": "t5-xl", + "downloads": 54, "source": "Hugging Face", - "score": -0.11351892743024095, - "first_commit": "2024-04-11 05:38:09", - "latest_commit": "2024-04-26 06:27:05", + "score": -0.09222233524729628, + "first_commit": "2023-04-26 07:19:08", + "latest_commit": "2023-05-10 10:01:04", "languages": [], "model_or_dataset": "model", - "model_size": 0.111, - "model_architectures": "BertForSequenceClassification" + "model_size": null, + "model_architectures": "T5ForConditionalGeneration" }, { - "description": "Google's mt5-base fine-tuned in Japanese to solve error detection and correction task. ", - "url": "https://huggingface.co/kz/mt5base-finetuned-ECC-japanese-small", - "project_name": "mt5base-finetuned-ECC-japanese-small", - "downloads": 59, + "description": "This is a Japanese+English sentence-BERT model.", + "url": "https://huggingface.co/sonoisa/sentence-bert-base-ja-en-mean-tokens", + "project_name": "sentence-bert-base-ja-en-mean-tokens", + "downloads": 54, "source": "Hugging Face", - "score": -0.11351892743024095, - "first_commit": "2021-03-21 19:07:13", - "latest_commit": "2022-05-26 13:50:56", + "score": -0.09222233524729628, + "first_commit": "2022-05-08 03:05:08", + "latest_commit": "2022-05-08 03:29:28", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "MT5ForConditionalGeneration" + "model_architectures": "BertModel" }, { - "description": "BERT base Japanese - JaQuAD Description A Japanese Question Answering model fine-tuned on JaQuAD.", - "url": "https://huggingface.co/SkelterLabsInc/bert-base-japanese-jaquad", - "project_name": "bert-base-japanese-jaquad", - "downloads": 59, + "description": "Heron BLIP Japanese StableLM", + "url": "https://huggingface.co/turing-motors/heron-chat-blip-ja-stablelm-base-7b-v1-llava-620k", + "project_name": "heron-chat-blip-ja-stablelm-base-7b-v1-llava-620k", + "downloads": 53, "source": "Hugging Face", - "score": -0.11351892743024095, - "first_commit": "2022-01-27 08:08:53", - "latest_commit": "2022-02-04 02:39:25", + "score": -0.09223294019783262, + "first_commit": "2024-02-27 13:48:02", + "latest_commit": "2024-02-27 13:59:23", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "BertForQuestionAnswering" + "model_architectures": "VideoBlipForConditionalGeneration" }, { - "description": "studio-ousia/luke-japanese-baseに対して次の変更を加えたモデルです。 ", - "url": "https://huggingface.co/uzabase/luke-japanese-wordpiece-base", - "project_name": "luke-japanese-wordpiece-base", - "downloads": 58, + "description": "BERT for Sentiment Analysis of Japanese Twitter", + "url": "https://huggingface.co/LoneWolfgang/bert-for-japanese-twitter-sentiment", + "project_name": "bert-for-japanese-twitter-sentiment", + "downloads": 53, "source": "Hugging Face", - "score": -0.11353463878693516, - "first_commit": "2023-08-10 06:04:58", - "latest_commit": "2023-11-28 13:35:07", + "score": -0.09223294019783262, + "first_commit": "2024-05-13 10:19:52", + "latest_commit": "2024-08-09 12:03:25", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LukeForMaskedLM" + "model_size": 0.111, + "model_architectures": "BertForSequenceClassification" }, { "description": "Oumuamua-7b-instruct-v2 🚨 If you want to avoid outputs that appear to be literal translations, please prompt this model to role-play as a Japanese person.", "url": "https://huggingface.co/nitky/Oumuamua-7b-instruct-v2", "project_name": "Oumuamua-7b-instruct-v2", - "downloads": 58, + "downloads": 53, "source": "Hugging Face", - "score": -0.11353463878693516, + "score": -0.09223294019783262, "first_commit": "2024-06-14 07:08:07", "latest_commit": "2024-06-19 22:29:07", "languages": [], @@ -9512,110 +9781,152 @@ "model_architectures": "MistralForCausalLM" }, { - "description": "COMET-GPT2 ja Finetuned GPT-2 on ATOMIC ja using a causal language modeling (CLM) objective.", - "url": "https://huggingface.co/nlp-waseda/comet-gpt2-small-japanese", - "project_name": "comet-gpt2-small-japanese", - "downloads": 57, + "description": "JSNLI Version 1.1 のデータセットのうち、フィルタリング後の訓練セット (train_w_filtering)", + "url": "https://huggingface.co/datasets/llm-book/jsnli", + "project_name": "jsnli", + "downloads": 53, "source": "Hugging Face", - "score": -0.11355035014362938, - "first_commit": "2022-11-15 05:14:35", - "latest_commit": "2023-02-13 10:26:12", + "score": -0.09223294019783262, + "first_commit": "2023-06-19 12:31:46", + "latest_commit": "2023-10-25 15:22:46", + "languages": [], + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null + }, + { + "description": "Convert from: drewschaub/whisper-large-v3-japanese-4k-steps Whisper large-v3 model for CTranslate2 This repository contains the conversion of drewschaub/whisper-large-v3-japanese-4k-steps to the CTranslate2 model format.", + "url": "https://huggingface.co/JhonVanced/whisper-large-v3-japanese-4k-steps-ct2", + "project_name": "whisper-large-v3-japanese-4k-steps-ct2", + "downloads": 52, + "source": "Hugging Face", + "score": -0.09224354514836895, + "first_commit": "2024-02-20 13:41:17", + "latest_commit": "2024-02-22 01:11:59", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "GPT2LMHeadModel" + "model_architectures": null }, { - "description": "whisper-large-v2-mix-jp model for CTranslate2 This repository contains the conversion of vumichien/whisper-large-v2-mix-jp to the CTranslate2 model format.", - "url": "https://huggingface.co/arc-r/faster-whisper-large-v2-mix-jp", - "project_name": "faster-whisper-large-v2-mix-jp", - "downloads": 57, + "description": "line-corporation/japanese-large-lm-1.7b-instruction-sft line-corporationさんが公開しているjapanese-large-lm-1.7b-instruction-sftのgguf変換版です。 ", + "url": "https://huggingface.co/mmnga/line-corp-japanese-large-lm-1.7b-instruction-sft-gguf", + "project_name": "line-corp-japanese-large-lm-1.7b-instruction-sft-gguf", + "downloads": 52, "source": "Hugging Face", - "score": -0.11355035014362938, - "first_commit": "2023-07-07 05:53:52", - "latest_commit": "2023-07-07 17:56:03", + "score": -0.09224354514836895, + "first_commit": "2023-09-03 22:30:23", + "latest_commit": "2024-03-24 05:54:56", "languages": [], "model_or_dataset": "model", "model_size": null, "model_architectures": null }, { - "description": "japanese-large-lm-3.6b-instruction-sft-8bit-1g-actorder_True", - "url": "https://huggingface.co/line-corporation/japanese-large-lm-3.6b-instruction-sft-8bit-1g-actorder_True", - "project_name": "japanese-large-lm-3.6b-instruction-sft-8bit-1g-actorder_True", - "downloads": 56, + "description": "japanese-large-lm-3.6b-instruction-sft-4bit-128g-actorder_False", + "url": "https://huggingface.co/line-corporation/japanese-large-lm-3.6b-instruction-sft-4bit-128g-actorder_False", + "project_name": "japanese-large-lm-3.6b-instruction-sft-4bit-128g-actorder_False", + "downloads": 52, "source": "Hugging Face", - "score": -0.1135660615003236, - "first_commit": "2023-09-26 06:16:23", - "latest_commit": "2023-09-28 00:02:06", + "score": -0.09224354514836895, + "first_commit": "2023-09-26 06:16:04", + "latest_commit": "2023-09-27 23:54:44", "languages": [], "model_or_dataset": "model", - "model_size": 1.17, + "model_size": 0.771, "model_architectures": "GPTNeoXForCausalLM" }, { - "description": "This is a Japanese+English sentence-BERT model.", - "url": "https://huggingface.co/sonoisa/sentence-bert-base-ja-en-mean-tokens", - "project_name": "sentence-bert-base-ja-en-mean-tokens", - "downloads": 56, + "description": "bert-base-japanese-v3-bpr-question-aio 「大規模言語モデル入門」の第9章で紹介している文書検索モデルBPRの質問エンコーダです。 ", + "url": "https://huggingface.co/llm-book/bert-base-japanese-v3-bpr-question-aio", + "project_name": "bert-base-japanese-v3-bpr-question-aio", + "downloads": 51, "source": "Hugging Face", - "score": -0.1135660615003236, - "first_commit": "2022-05-08 03:05:08", - "latest_commit": "2022-05-08 03:29:28", + "score": -0.0922541500989053, + "first_commit": "2023-06-06 08:21:13", + "latest_commit": "2023-07-24 07:12:05", "languages": [], "model_or_dataset": "model", "model_size": null, "model_architectures": "BertModel" }, { - "description": "Ninja-v1-RP-expressive-v2 GGUF版はこちら/Click here for the GGUF version 概要 This is a merge of pre-trained language models created using mergekit. ", - "url": "https://huggingface.co/Aratako/Ninja-v1-RP-expressive-v2", - "project_name": "Ninja-v1-RP-expressive-v2", - "downloads": 56, + "description": "I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information japanese-stablelm-3b-4e1t-instruct - GGUF Model creator: stabilityai Original model: japanese-stablelm-3b-4e1t-instruct StableLM", + "url": "https://huggingface.co/maddes8cht/stabilityai-japanese-stablelm-3b-4e1t-instruct-gguf", + "project_name": "stabilityai-japanese-stablelm-3b-4e1t-instruct-gguf", + "downloads": 50, "source": "Hugging Face", - "score": -0.1135660615003236, - "first_commit": "2024-05-25 16:56:18", - "latest_commit": "2024-05-26 15:20:52", + "score": -0.09226475504944162, + "first_commit": "2023-11-16 10:25:20", + "latest_commit": "2023-11-16 12:53:33", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": "MistralForCausalLM" + "model_size": 2.8, + "model_architectures": null }, { - "description": "Japanese-LLaMA-2-13B-GGUF Japanese-LLaMA-2-13B-GGUFはJapanese-LLaMA-2-13BのGGUF形式です。 ", - "url": "https://huggingface.co/owner203/japanese-llama-2-13b-gguf", - "project_name": "japanese-llama-2-13b-gguf", - "downloads": 56, + "description": "japanese-large-lm-1.7b-instruction-sft-4bit-128g-actorder_False", + "url": "https://huggingface.co/line-corporation/japanese-large-lm-1.7b-instruction-sft-4bit-128g-actorder_False", + "project_name": "japanese-large-lm-1.7b-instruction-sft-4bit-128g-actorder_False", + "downloads": 50, "source": "Hugging Face", - "score": -0.1135660615003236, - "first_commit": "2023-12-20 05:37:09", - "latest_commit": "2023-12-26 11:45:15", + "score": -0.09226475504944162, + "first_commit": "2023-09-26 06:15:16", + "latest_commit": "2023-09-29 03:19:23", "languages": [], "model_or_dataset": "model", - "model_size": 13.3, - "model_architectures": null + "model_size": 0.446, + "model_architectures": "GPT2LMHeadModel" }, { - "description": "llm-book/bert-base-japanese-v3-crf-ner-wikipedia-dataset 「大規模言語モデル入門」の第6章で紹介している固有表現認識のモデルです。 ", - "url": "https://huggingface.co/llm-book/bert-base-japanese-v3-crf-ner-wikipedia-dataset", - "project_name": "bert-base-japanese-v3-crf-ner-wikipedia-dataset", - "downloads": 55, + "description": "bert-base-japanese-jsnli This model is a fine-tuned version of cl-tohoku/bert-base-japanese-v2 on the JSNLI dataset.", + "url": "https://huggingface.co/Formzu/bert-base-japanese-jsnli", + "project_name": "bert-base-japanese-jsnli", + "downloads": 49, "source": "Hugging Face", - "score": -0.11358177285701782, - "first_commit": "2023-05-28 08:19:43", - "latest_commit": "2023-07-25 15:04:39", + "score": -0.09227535999997796, + "first_commit": "2022-10-14 07:50:13", + "latest_commit": "2022-10-18 12:13:20", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "BertWithCrfForTokenClassification" + "model_architectures": "BertForSequenceClassification" + }, + { + "description": "electra-base-cyberbullying This is an ELECTRA Base model for the Japanese language finetuned for automatic cyberbullying detection.", + "url": "https://huggingface.co/kit-nlp/transformers-ud-japanese-electra-base-discriminator-cyberbullying", + "project_name": "transformers-ud-japanese-electra-base-discriminator-cyberbullying", + "downloads": 49, + "source": "Hugging Face", + "score": -0.09227535999997796, + "first_commit": "2022-09-09 04:08:15", + "latest_commit": "2022-11-01 07:18:40", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "ElectraForSequenceClassification" + }, + { + "description": "このモデルはluke-japanese-baseをファインチューニングして、MARC-ja(positive or negativeの二値分類)に用いれるようにしたものです。 ", + "url": "https://huggingface.co/Mizuiro-sakura/luke-japanese-base-marcja", + "project_name": "luke-japanese-base-marcja", + "downloads": 48, + "source": "Hugging Face", + "score": -0.09228596495051429, + "first_commit": "2023-03-02 03:57:33", + "latest_commit": "2023-07-21 14:10:48", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.279, + "model_architectures": "LukeForSequenceClassification" }, { "description": "t5-base-japanese-web-8k (with Byte-fallback, 8K) Description megagonlabs/t5-base-japanese-web-8k is a T5 (Text-to-Text Transfer Transformer) model pre-trained on Japanese web texts.", "url": "https://huggingface.co/megagonlabs/t5-base-japanese-web-8k", "project_name": "t5-base-japanese-web-8k", - "downloads": 55, + "downloads": 48, "source": "Hugging Face", - "score": -0.11358177285701782, + "score": -0.09228596495051429, "first_commit": "2021-09-06 10:13:42", "latest_commit": "2023-07-04 07:05:38", "languages": [], @@ -9624,194 +9935,180 @@ "model_architectures": "T5ForConditionalGeneration" }, { - "description": "japanese-large-lm-3.6b-instruction-sft-4bit-128g-actorder_False", - "url": "https://huggingface.co/line-corporation/japanese-large-lm-3.6b-instruction-sft-4bit-128g-actorder_False", - "project_name": "japanese-large-lm-3.6b-instruction-sft-4bit-128g-actorder_False", - "downloads": 54, + "description": "Cross-Encoder for Natural Language Inference(NLI) for Japanese Considering the results of the JNLI evaluation result, we recommend using akiFQC/bert-base-japanese-v3_nli-jsnli-jnli-jsick for natural language inference in Japanese.", + "url": "https://huggingface.co/akiFQC/bert-base-japanese-v3_nli-jsnli", + "project_name": "bert-base-japanese-v3_nli-jsnli", + "downloads": 48, "source": "Hugging Face", - "score": -0.11359748421371203, - "first_commit": "2023-09-26 06:16:04", - "latest_commit": "2023-09-27 23:54:44", + "score": -0.09228596495051429, + "first_commit": "2024-04-11 05:38:09", + "latest_commit": "2024-04-26 06:27:05", "languages": [], "model_or_dataset": "model", - "model_size": 0.771, - "model_architectures": "GPTNeoXForCausalLM" + "model_size": 0.111, + "model_architectures": "BertForSequenceClassification" }, { - "description": "Miwa-Keita/zenz-v1-checkpoints を optimum 用に ONNX に変換したモデルです。", - "url": "https://huggingface.co/p1atdev/zenz-v1-onnx", - "project_name": "zenz-v1-onnx", - "downloads": 54, + "description": "Mixtral-8x7B-v0.1-japanese Mixtral-8x7B-v0.1-japaneseはMixtral-8x7B-v0.1をベースに日本語の語彙拡張継続事前学習を実施したモデルです。", + "url": "https://huggingface.co/abeja/Mixtral-8x7B-v0.1-japanese", + "project_name": "Mixtral-8x7B-v0.1-japanese", + "downloads": 48, "source": "Hugging Face", - "score": -0.11359748421371203, - "first_commit": "2024-06-29 03:03:03", - "latest_commit": "2024-06-29 03:40:34", + "score": -0.09228596495051429, + "first_commit": "2024-04-16 03:06:14", + "latest_commit": "2024-04-20 09:14:10", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "GPT2LMHeadModel" + "model_size": 46.9, + "model_architectures": "MixtralForCausalLM" }, { - "description": "alpaca-guanaco-japanese-gpt-1b 1.3Bパラメータの日本語GPTモデルを使用した対話AIです。", - "url": "https://huggingface.co/inu-ai/alpaca-guanaco-japanese-gpt-1b", - "project_name": "alpaca-guanaco-japanese-gpt-1b", - "downloads": 54, + "description": "実験モデルです。", + "url": "https://huggingface.co/Akimite/Qwen2-7b-Instruct-Boku-v2", + "project_name": "Qwen2-7b-Instruct-Boku-v2", + "downloads": 47, "source": "Hugging Face", - "score": -0.11359748421371203, - "first_commit": "2023-04-12 00:18:29", - "latest_commit": "2023-04-13 10:25:48", + "score": -0.09229656990105062, + "first_commit": "2024-06-13 03:23:05", + "latest_commit": "2024-06-15 14:58:10", "languages": [], "model_or_dataset": "model", - "model_size": 1.33, - "model_architectures": "GPT2LMHeadModel" + "model_size": 7.62, + "model_architectures": "Qwen2ForCausalLM" }, { - "description": "japanese-large-lm-1.7b-instruction-sft-4bit-128g-actorder_False", - "url": "https://huggingface.co/line-corporation/japanese-large-lm-1.7b-instruction-sft-4bit-128g-actorder_False", - "project_name": "japanese-large-lm-1.7b-instruction-sft-4bit-128g-actorder_False", - "downloads": 53, + "description": "COMET-T5 ja Finetuned T5 on ATOMIC ja using a text-to-text language modeling objective.", + "url": "https://huggingface.co/nlp-waseda/comet-t5-base-japanese", + "project_name": "comet-t5-base-japanese", + "downloads": 46, "source": "Hugging Face", - "score": -0.11361319557040625, - "first_commit": "2023-09-26 06:15:16", - "latest_commit": "2023-09-29 03:19:23", + "score": -0.09230717485158696, + "first_commit": "2022-11-12 15:07:40", + "latest_commit": "2023-02-08 09:26:55", "languages": [], "model_or_dataset": "model", - "model_size": 0.446, - "model_architectures": "GPT2LMHeadModel" + "model_size": null, + "model_architectures": "T5ForConditionalGeneration" }, { - "description": "Heron BLIP Japanese StableLM", - "url": "https://huggingface.co/turing-motors/heron-chat-blip-ja-stablelm-base-7b-v1-llava-620k", - "project_name": "heron-chat-blip-ja-stablelm-base-7b-v1-llava-620k", - "downloads": 53, + "description": "Oumuamua-7b-instruct This is a merge of pre-trained language models created using mergekit. ", + "url": "https://huggingface.co/nitky/Oumuamua-7b-instruct", + "project_name": "Oumuamua-7b-instruct", + "downloads": 46, "source": "Hugging Face", - "score": -0.11361319557040625, - "first_commit": "2024-02-27 13:48:02", - "latest_commit": "2024-02-27 13:59:23", + "score": -0.09230717485158696, + "first_commit": "2024-06-01 10:40:37", + "latest_commit": "2024-06-01 15:55:51", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "VideoBlipForConditionalGeneration" + "model_size": 7.33, + "model_architectures": "MistralForCausalLM" }, { - "description": "Japanese-Alpaca-2-13B-GGUF Japanese-Alpaca-2-13B-GGUFはJapanese-Alpaca-2-13BのGGUF形式です。 ", - "url": "https://huggingface.co/owner203/japanese-alpaca-2-13b-gguf", - "project_name": "japanese-alpaca-2-13b-gguf", - "downloads": 53, + "description": "Overview of bert-japanese-12M The bert-japanese-12M model is a transformer-based model with BERT architecture, which is designed to be used on Japanese text.", + "url": "https://huggingface.co/nptdat/bert-japanese-12M", + "project_name": "bert-japanese-12M", + "downloads": 46, "source": "Hugging Face", - "score": -0.11361319557040625, - "first_commit": "2023-12-20 10:56:08", - "latest_commit": "2023-12-26 11:46:41", + "score": -0.09230717485158696, + "first_commit": "2024-08-16 16:46:49", + "latest_commit": "2024-08-19 02:56:14", "languages": [], "model_or_dataset": "model", - "model_size": 13.3, - "model_architectures": null + "model_size": null, + "model_architectures": "BertForMaskedLM" }, { - "description": "Original Model Optical character recognition for Japanese text, with the main focus being Japanese manga.", - "url": "https://huggingface.co/TareHimself/manga-ocr-base", - "project_name": "manga-ocr-base", - "downloads": 53, + "description": "Ruri-Reranker: Japanese General Reranker Usage Direct Usage (Sentence Transformers)", + "url": "https://huggingface.co/cl-nagoya/ruri-reranker-small", + "project_name": "ruri-reranker-small", + "downloads": 45, "source": "Hugging Face", - "score": -0.11361319557040625, - "first_commit": "2023-09-14 04:15:52", - "latest_commit": "2024-06-03 05:10:11", + "score": -0.09231777980212329, + "first_commit": "2024-08-19 12:39:07", + "latest_commit": "2024-09-04 08:50:32", "languages": [], "model_or_dataset": "model", - "model_size": 0.111, - "model_architectures": "VisionEncoderDecoderModel" + "model_size": 0.06870000000000001, + "model_architectures": "DistilBertForSequenceClassification" }, { - "description": "実験モデルです。", - "url": "https://huggingface.co/Akimite/Qwen2-7b-Instruct-Boku-v2", - "project_name": "Qwen2-7b-Instruct-Boku-v2", - "downloads": 52, + "description": "ELYZA-japanese-CodeLlama-7b-instruct-GPTQ-calib-ja-1k elyzaさんが公開しているELYZA-japanese-CodeLlama-7b-instructを 日本語のキャリブレーションセットで生成したGPTQモデルになります。", + "url": "https://huggingface.co/mmnga/ELYZA-japanese-CodeLlama-7b-instruct-GPTQ-calib-ja-1k", + "project_name": "ELYZA-japanese-CodeLlama-7b-instruct-GPTQ-calib-ja-1k", + "downloads": 45, "source": "Hugging Face", - "score": -0.11362890692710047, - "first_commit": "2024-06-13 03:23:05", - "latest_commit": "2024-06-15 14:58:10", + "score": -0.09231777980212329, + "first_commit": "2023-11-15 16:33:25", + "latest_commit": "2023-11-16 14:28:39", "languages": [], "model_or_dataset": "model", - "model_size": 7.62, - "model_architectures": "Qwen2ForCausalLM" + "model_size": null, + "model_architectures": "LlamaForCausalLM" }, { - "description": "Fine-tuned XLSR-53 large model for speech diarization in Japanese phone-call 2 speakers diarization model which was fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using phone-call data CallHome.", - "url": "https://huggingface.co/Ivydata/wav2vec2-large-speech-diarization-jp", - "project_name": "wav2vec2-large-speech-diarization-jp", - "downloads": 51, + "description": "bert-base-japanese-v3-jcommonsenseqa 「大規模言語モデル入門」の第5章で紹介している(多肢選択式質問応答)のモデルです。 ", + "url": "https://huggingface.co/llm-book/bert-base-japanese-v3-jcommonsenseqa", + "project_name": "bert-base-japanese-v3-jcommonsenseqa", + "downloads": 45, "source": "Hugging Face", - "score": -0.11364461828379468, - "first_commit": "2023-05-08 10:10:43", - "latest_commit": "2023-05-10 00:32:23", + "score": -0.09231777980212329, + "first_commit": "2023-06-20 07:01:53", + "latest_commit": "2023-07-24 06:49:16", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "Wav2Vec2ForAudioFrameClassification" + "model_architectures": "BertForMultipleChoice" }, { - "description": "JSNLI Version 1.1 のデータセットのうち、フィルタリング後の訓練セット (train_w_filtering)", - "url": "https://huggingface.co/datasets/llm-book/jsnli", - "project_name": "jsnli", - "downloads": 51, + "description": "[Under Construction]", + "url": "https://huggingface.co/datasets/bclavie/mmarco-japanese-hard-negatives", + "project_name": "mmarco-japanese-hard-negatives", + "downloads": 45, "source": "Hugging Face", - "score": -0.11364461828379468, - "first_commit": "2023-06-19 12:31:46", - "latest_commit": "2023-10-25 15:22:46", + "score": -0.09231777980212329, + "first_commit": "2023-12-24 13:04:27", + "latest_commit": "2023-12-24 18:52:04", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "mathstral-7B-v0.1-gguf mistralaiさんが公開しているmathstral-7B-v0.1のggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/mathstral-7B-v0.1-gguf", - "project_name": "mathstral-7B-v0.1-gguf", - "downloads": 50, - "source": "Hugging Face", - "score": -0.1136603296404889, - "first_commit": "2024-07-17 17:49:56", - "latest_commit": "2024-07-17 18:54:27", - "languages": [], - "model_or_dataset": "model", - "model_size": 7.25, - "model_architectures": null - }, - { - "description": "matsuolab-weblab-10b-instruction-sft-gguf matsuo-labさんが公開しているweblab-10b-instruction-sftのggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/matsuolab-weblab-10b-instruction-sft-gguf", - "project_name": "matsuolab-weblab-10b-instruction-sft-gguf", - "downloads": 49, + "description": "cyberagent/calm2-7b-chatの出力を人手でチェック・修正することで作成した日本語Instructionデータセットです。 ", + "url": "https://huggingface.co/datasets/Kendamarron/jimba-instuction-1k-beta", + "project_name": "jimba-instuction-1k-beta", + "downloads": 45, "source": "Hugging Face", - "score": -0.11367604099718312, - "first_commit": "2023-08-21 11:22:48", - "latest_commit": "2023-09-02 18:16:33", + "score": -0.09231777980212329, + "first_commit": "2024-02-29 15:23:48", + "latest_commit": "2024-04-25 12:49:28", "languages": [], - "model_or_dataset": "model", - "model_size": 10.7, + "model_or_dataset": "dataset", + "model_size": null, "model_architectures": null }, { - "description": "Oumuamua-7b-instruct This is a merge of pre-trained language models created using mergekit. ", - "url": "https://huggingface.co/nitky/Oumuamua-7b-instruct", - "project_name": "Oumuamua-7b-instruct", - "downloads": 49, + "description": "deberta-large-japanese-wikipedia-luw-upos Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-wikipedia-luw-upos", + "project_name": "deberta-large-japanese-wikipedia-luw-upos", + "downloads": 44, "source": "Hugging Face", - "score": -0.11367604099718312, - "first_commit": "2024-06-01 10:40:37", - "latest_commit": "2024-06-01 15:55:51", + "score": -0.09232838475265963, + "first_commit": "2022-07-06 03:15:12", + "latest_commit": "2024-08-20 17:54:58", "languages": [], "model_or_dataset": "model", - "model_size": 7.33, - "model_architectures": "MistralForCausalLM" + "model_size": null, + "model_architectures": "DebertaV2ForTokenClassification" }, { "description": "japanese-large-lm-1.7b-instruction-sft-8bit-1g-actorder_True", "url": "https://huggingface.co/line-corporation/japanese-large-lm-1.7b-instruction-sft-8bit-1g-actorder_True", "project_name": "japanese-large-lm-1.7b-instruction-sft-8bit-1g-actorder_True", - "downloads": 48, + "downloads": 44, "source": "Hugging Face", - "score": -0.11369175235387734, + "score": -0.09232838475265963, "first_commit": "2023-09-26 06:15:31", "latest_commit": "2023-09-29 03:09:03", "languages": [], @@ -9820,54 +10117,110 @@ "model_architectures": "GPT2LMHeadModel" }, { - "description": "Japanese-LLaMA-2-7B-GGUF Japanese-LLaMA-2-7B-GGUFはJapanese-LLaMA-2-7BのGGUF形式です。 ", - "url": "https://huggingface.co/owner203/japanese-llama-2-7b-gguf", - "project_name": "japanese-llama-2-7b-gguf", - "downloads": 48, + "description": "オリジナルのサイトと同じものを使用しています。 ", + "url": "https://huggingface.co/datasets/llm-book/ja-vicuna-qa-benchmark", + "project_name": "ja-vicuna-qa-benchmark", + "downloads": 44, "source": "Hugging Face", - "score": -0.11369175235387734, - "first_commit": "2024-01-22 03:00:02", - "latest_commit": "2024-06-05 02:30:01", + "score": -0.09232838475265963, + "first_commit": "2024-06-25 22:14:55", + "latest_commit": "2024-08-31 12:37:25", "languages": [], - "model_or_dataset": "model", - "model_size": 6.97, + "model_or_dataset": "dataset", + "model_size": null, "model_architectures": null }, { - "description": "英語+日本語T5事前学習済みモデル This is a T5 (Text-to-Text Transfer Transformer) model pretrained on English and Japanese balanced corpus. ", - "url": "https://huggingface.co/sonoisa/t5-base-english-japanese", - "project_name": "t5-base-english-japanese", - "downloads": 48, + "description": "Ruri-Reranker: Japanese General Reranker Usage Direct Usage (Sentence Transformers)", + "url": "https://huggingface.co/cl-nagoya/ruri-reranker-base", + "project_name": "ruri-reranker-base", + "downloads": 43, "source": "Hugging Face", - "score": -0.11369175235387734, - "first_commit": "2022-07-28 11:31:28", - "latest_commit": "2022-08-27 09:07:53", + "score": -0.09233898970319596, + "first_commit": "2024-08-20 01:10:40", + "latest_commit": "2024-09-04 08:50:21", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.111, + "model_architectures": "BertForSequenceClassification" + }, + { + "description": "bert-japanese_finetuned-sentiment-analysis This model was trained from scratch on the Japanese Sentiment Polarity Dictionary dataset.", + "url": "https://huggingface.co/minutillamolinara/bert-japanese_finetuned-sentiment-analysis", + "project_name": "bert-japanese_finetuned-sentiment-analysis", + "downloads": 43, + "source": "Hugging Face", + "score": -0.09233898970319596, + "first_commit": "2023-03-31 02:28:09", + "latest_commit": "2023-03-31 13:13:37", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "T5ForConditionalGeneration" + "model_architectures": "BertForSequenceClassification" }, { - "description": "bert-base-japanese-v3-bpr-question-aio 「大規模言語モデル入門」の第9章で紹介している文書検索モデルBPRの質問エンコーダです。 ", - "url": "https://huggingface.co/llm-book/bert-base-japanese-v3-bpr-question-aio", - "project_name": "bert-base-japanese-v3-bpr-question-aio", - "downloads": 47, + "description": "whisper-large-v2-mix-jp model for CTranslate2 This repository contains the conversion of vumichien/whisper-large-v2-mix-jp to the CTranslate2 model format.", + "url": "https://huggingface.co/arc-r/faster-whisper-large-v2-mix-jp", + "project_name": "faster-whisper-large-v2-mix-jp", + "downloads": 43, "source": "Hugging Face", - "score": -0.11370746371057155, - "first_commit": "2023-06-06 08:21:13", - "latest_commit": "2023-07-24 07:12:05", + "score": -0.09233898970319596, + "first_commit": "2023-07-07 05:53:52", + "latest_commit": "2023-07-07 17:56:03", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "BertModel" + "model_architectures": null + }, + { + "description": "Model trained on 800,000 Japanese sentences after reducing oshizo/japanese-e5-mistral-7b_slerp to 8 layers.", + "url": "https://huggingface.co/oshizo/japanese-e5-mistral-1.9b", + "project_name": "japanese-e5-mistral-1.9b", + "downloads": 43, + "source": "Hugging Face", + "score": -0.09233898970319596, + "first_commit": "2024-02-02 12:39:11", + "latest_commit": "2024-02-03 00:28:28", + "languages": [], + "model_or_dataset": "model", + "model_size": 1.88, + "model_architectures": "MistralForEmbedding" + }, + { + "description": "alpaca-guanaco-japanese-gpt-1b 1.3Bパラメータの日本語GPTモデルを使用した対話AIです。", + "url": "https://huggingface.co/inu-ai/alpaca-guanaco-japanese-gpt-1b", + "project_name": "alpaca-guanaco-japanese-gpt-1b", + "downloads": 43, + "source": "Hugging Face", + "score": -0.09233898970319596, + "first_commit": "2023-04-12 00:18:29", + "latest_commit": "2023-04-13 10:25:48", + "languages": [], + "model_or_dataset": "model", + "model_size": 1.33, + "model_architectures": "GPT2LMHeadModel" + }, + { + "description": "japanese-large-lm-3.6b-instruction-sft-4bit-32g-actorder_False", + "url": "https://huggingface.co/line-corporation/japanese-large-lm-3.6b-instruction-sft-4bit-32g-actorder_False", + "project_name": "japanese-large-lm-3.6b-instruction-sft-4bit-32g-actorder_False", + "downloads": 43, + "source": "Hugging Face", + "score": -0.09233898970319596, + "first_commit": "2023-09-26 06:15:51", + "latest_commit": "2023-09-27 23:56:05", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.861, + "model_architectures": "GPTNeoXForCausalLM" }, { "description": "SambaLingo-Japanese-Chat SambaLingo-Japanese-Chat is a human aligned chat model trained in Japanese and English.", "url": "https://huggingface.co/LoneStriker/SambaLingo-Japanese-Chat-GGUF", "project_name": "SambaLingo-Japanese-Chat-GGUF", - "downloads": 47, + "downloads": 42, "source": "Hugging Face", - "score": -0.11370746371057155, + "score": -0.0923495946537323, "first_commit": "2024-03-07 06:38:01", "latest_commit": "2024-03-07 06:48:27", "languages": [], @@ -9876,152 +10229,194 @@ "model_architectures": null }, { - "description": "名言推論モデル", - "url": "https://huggingface.co/Momerio/meigen_generate_Japanese", - "project_name": "meigen_generate_Japanese", - "downloads": 47, + "description": "Japanese to Korean translator Japanese to Korean translator model based on EncoderDecoderModel(bert-japanese+kogpt2)", + "url": "https://huggingface.co/sappho192/aihub-ja-ko-translator", + "project_name": "aihub-ja-ko-translator", + "downloads": 42, "source": "Hugging Face", - "score": -0.11370746371057155, - "first_commit": "2021-10-13 15:30:14", - "latest_commit": "2021-10-26 01:19:59", + "score": -0.0923495946537323, + "first_commit": "2024-02-05 00:51:47", + "latest_commit": "2024-06-28 06:38:39", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.265, + "model_architectures": "EncoderDecoderModel" + }, + { + "description": "rinna/japanese-data2vec-audio-base Overview This is a Japanese data2vec Audio Base model trained by rinna Co.", + "url": "https://huggingface.co/rinna/japanese-data2vec-audio-base", + "project_name": "japanese-data2vec-audio-base", + "downloads": 41, + "source": "Hugging Face", + "score": -0.09236019960426863, + "first_commit": "2024-03-05 10:32:32", + "latest_commit": "2024-07-22 08:12:56", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.0932, + "model_architectures": "Data2VecAudioModel" + }, + { + "description": "nlp-waseda/bigbird-base-japanese Model description This is a Japanese BigBird base model pretrained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.", + "url": "https://huggingface.co/nlp-waseda/bigbird-base-japanese", + "project_name": "bigbird-base-japanese", + "downloads": 41, + "source": "Hugging Face", + "score": -0.09236019960426863, + "first_commit": "2023-06-03 12:51:12", + "latest_commit": "2023-06-20 10:49:17", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "GPT2LMHeadModel" + "model_architectures": "BigBirdForMaskedLM" }, { - "description": "roberta_qa_japanese (Japanese caption : 日本語の (抽出型) 質問応答のモデル)", - "url": "https://huggingface.co/tsmatz/roberta_qa_japanese", - "project_name": "roberta_qa_japanese", - "downloads": 46, + "description": "japanese-large-lm-1.7b-instruction-sft-4bit-32g-actorder_False", + "url": "https://huggingface.co/line-corporation/japanese-large-lm-1.7b-instruction-sft-4bit-32g-actorder_False", + "project_name": "japanese-large-lm-1.7b-instruction-sft-4bit-32g-actorder_False", + "downloads": 41, "source": "Hugging Face", - "score": -0.11372317506726577, - "first_commit": "2022-12-11 03:41:07", - "latest_commit": "2024-07-12 00:00:07", + "score": -0.09236019960426863, + "first_commit": "2023-09-26 06:14:25", + "latest_commit": "2023-09-27 01:23:34", "languages": [], "model_or_dataset": "model", - "model_size": 0.11, - "model_architectures": "RobertaForQuestionAnswering" + "model_size": 0.487, + "model_architectures": "GPT2LMHeadModel" }, { - "description": "Dataset Summary SNOW T15:The simplified corpus for the Japanese language.", - "url": "https://huggingface.co/datasets/SNOW-NLP/snow_simplified_japanese_corpus", - "project_name": "snow_simplified_japanese_corpus", - "downloads": 46, + "description": "Wikipedia日本語版データセット(izumi-lab/wikipedia-ja-20230720)", + "url": "https://huggingface.co/datasets/shi3z/Japanese_Wikipedia_Conversation", + "project_name": "Japanese_Wikipedia_Conversation", + "downloads": 41, "source": "Hugging Face", - "score": -0.11372317506726577, - "first_commit": "2022-01-25 16:36:23", - "latest_commit": "2024-01-18 11:16:01", + "score": -0.09236019960426863, + "first_commit": "2023-11-10 07:36:40", + "latest_commit": "2023-11-10 22:46:29", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "275.86Mのmixtralを日本語データセットでpretrainingしたものです sample from transformers import AutoTokenizer, AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained(\"if001/tiny_mixtral_ja\")", - "url": "https://huggingface.co/hibikaze/tiny_mixtral_ja_with_tokenizer", - "project_name": "tiny_mixtral_ja_with_tokenizer", - "downloads": 45, + "description": "つくよみちゃんデータセットを用いて calm-2-7b-chat をファインチューニングしたモデルです。", + "url": "https://huggingface.co/offtoung/tsukuyomi-chan-calm2-7b", + "project_name": "tsukuyomi-chan-calm2-7b", + "downloads": 39, "source": "Hugging Face", - "score": -0.11373888642395999, - "first_commit": "2024-07-20 05:30:59", - "latest_commit": "2024-07-20 05:33:38", + "score": -0.0923814095053413, + "first_commit": "2023-12-21 08:46:37", + "latest_commit": "2023-12-27 04:07:20", "languages": [], "model_or_dataset": "model", - "model_size": 0.276, - "model_architectures": "MixtralForCausalLM" + "model_size": 7.01, + "model_architectures": "LlamaForCausalLM" }, { - "description": "Overview of bert-japanese-12M The bert-japanese-12M model is a transformer-based model with BERT architecture, which is designed to be used on Japanese text.", - "url": "https://huggingface.co/nptdat/bert-japanese-12M", - "project_name": "bert-japanese-12M", - "downloads": 45, + "description": "rinna/nekomata-7b-instruction-gguf Overview The model is the GGUF version of rinna/nekomata-7b-instruction.", + "url": "https://huggingface.co/rinna/nekomata-7b-instruction-gguf", + "project_name": "nekomata-7b-instruction-gguf", + "downloads": 39, "source": "Hugging Face", - "score": -0.11373888642395999, - "first_commit": "2024-08-16 16:46:49", - "latest_commit": "2024-08-19 02:56:14", + "score": -0.0923814095053413, + "first_commit": "2023-12-19 08:11:08", + "latest_commit": "2024-07-20 08:38:34", "languages": [], "model_or_dataset": "model", + "model_size": 7.72, + "model_architectures": null + }, + { + "description": "Dataset Details Dataset Type:Japanese LLaVA v1.5", + "url": "https://huggingface.co/datasets/turing-motors/LLaVA-v1.5-Instruct-620K-JA", + "project_name": "LLaVA-v1.5-Instruct-620K-JA", + "downloads": 39, + "source": "Hugging Face", + "score": -0.0923814095053413, + "first_commit": "2024-04-10 05:04:58", + "latest_commit": "2024-04-12 09:18:42", + "languages": [], + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "BertForMaskedLM" + "model_architectures": null }, { - "description": "japanese-large-lm-3.6b-instruction-sft-4bit-32g-actorder_False", - "url": "https://huggingface.co/line-corporation/japanese-large-lm-3.6b-instruction-sft-4bit-32g-actorder_False", - "project_name": "japanese-large-lm-3.6b-instruction-sft-4bit-32g-actorder_False", - "downloads": 44, + "description": "This dataset is the data that corrected the translation errors and untranslated data of the Japanese data in MBZUAI/multilingual-llava-bench-in-the-wild.", + "url": "https://huggingface.co/datasets/toshi456/llava-bench-in-the-wild-ja", + "project_name": "llava-bench-in-the-wild-ja", + "downloads": 39, "source": "Hugging Face", - "score": -0.1137545977806542, - "first_commit": "2023-09-26 06:15:51", - "latest_commit": "2023-09-27 23:56:05", + "score": -0.0923814095053413, + "first_commit": "2024-03-06 21:56:53", + "latest_commit": "2024-04-01 15:15:57", "languages": [], - "model_or_dataset": "model", - "model_size": 0.861, - "model_architectures": "GPTNeoXForCausalLM" + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null }, { - "description": "BERT for Sentiment Analysis of Japanese Twitter", - "url": "https://huggingface.co/LoneWolfgang/bert-for-japanese-twitter-sentiment", - "project_name": "bert-for-japanese-twitter-sentiment", - "downloads": 44, + "description": "Sarashina2-7B Instruct sarashina2-7Bを会話できるようにフルファインチューニングしたものです。", + "url": "https://huggingface.co/alfredplpl/sarashina2-7b-it", + "project_name": "sarashina2-7b-it", + "downloads": 38, "source": "Hugging Face", - "score": -0.1137545977806542, - "first_commit": "2024-05-13 10:19:52", - "latest_commit": "2024-08-09 12:03:25", + "score": -0.09239201445587764, + "first_commit": "2024-06-12 02:24:28", + "latest_commit": "2024-06-12 03:00:35", "languages": [], "model_or_dataset": "model", - "model_size": 0.111, - "model_architectures": "BertForSequenceClassification" + "model_size": 7.32, + "model_architectures": "LlamaForCausalLM" }, { - "description": "japanese-large-lm-1.7b-instruction-sft-4bit-32g-actorder_False", - "url": "https://huggingface.co/line-corporation/japanese-large-lm-1.7b-instruction-sft-4bit-32g-actorder_False", - "project_name": "japanese-large-lm-1.7b-instruction-sft-4bit-32g-actorder_False", - "downloads": 44, + "description": "zenz-v1 zenz-v1はGPT-2アーキテクチャに基づくかな漢字変換タスクに特化した言語モデルです。", + "url": "https://huggingface.co/Miwa-Keita/zenz-v1", + "project_name": "zenz-v1", + "downloads": 38, "source": "Hugging Face", - "score": -0.1137545977806542, - "first_commit": "2023-09-26 06:14:25", - "latest_commit": "2023-09-27 01:23:34", + "score": -0.09239201445587764, + "first_commit": "2024-05-12 15:48:46", + "latest_commit": "2024-05-13 16:34:02", "languages": [], "model_or_dataset": "model", - "model_size": 0.487, + "model_size": 0.09509999999999999, "model_architectures": "GPT2LMHeadModel" }, { - "description": "Mixtral-8x7B-v0.1-japanese Mixtral-8x7B-v0.1-japaneseはMixtral-8x7B-v0.1をベースに日本語の語彙拡張継続事前学習を実施したモデルです。", - "url": "https://huggingface.co/abeja/Mixtral-8x7B-v0.1-japanese", - "project_name": "Mixtral-8x7B-v0.1-japanese", - "downloads": 43, + "description": "One more step before getting this model.", + "url": "https://huggingface.co/rinna/japanese-stable-diffusion", + "project_name": "japanese-stable-diffusion", + "downloads": 38, "source": "Hugging Face", - "score": -0.11377030913734842, - "first_commit": "2024-04-16 03:06:14", - "latest_commit": "2024-04-20 09:14:10", + "score": -0.09239201445587764, + "first_commit": null, + "latest_commit": null, "languages": [], "model_or_dataset": "model", - "model_size": 46.9, - "model_architectures": "MixtralForCausalLM" + "model_size": null, + "model_architectures": null }, { - "description": "bert-base-japanese-v3-jcommonsenseqa 「大規模言語モデル入門」の第5章で紹介している(多肢選択式質問応答)のモデルです。 ", - "url": "https://huggingface.co/llm-book/bert-base-japanese-v3-jcommonsenseqa", - "project_name": "bert-base-japanese-v3-jcommonsenseqa", - "downloads": 43, + "description": "以下のデータ源からランダムに抽出した日本語のテキストをもとに､RAG形式のQ&Aを自動生成したものです｡ Wikibooks Wikipedia 判例データ instruction datasetとしてではなく､事前学習での利用を想定しています(質疑応答をするための訓練)｡ 一部の計算には東京工業大学のスーパーコンピュータTSUBAME4.0を利用しました｡", + "url": "https://huggingface.co/datasets/kanhatakeyama/CreativeCommons-RAG-QA-Mixtral8x22b", + "project_name": "CreativeCommons-RAG-QA-Mixtral8x22b", + "downloads": 38, "source": "Hugging Face", - "score": -0.11377030913734842, - "first_commit": "2023-06-20 07:01:53", - "latest_commit": "2023-07-24 06:49:16", + "score": -0.09239201445587764, + "first_commit": "2024-07-03 07:54:49", + "latest_commit": "2024-07-12 06:43:18", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "BertForMultipleChoice" + "model_architectures": null }, { "description": "ELECTRA base Japanese discriminator This is a ELECTRA model pretrained on texts in the Japanese language.", "url": "https://huggingface.co/izumi-lab/electra-base-japanese-discriminator", "project_name": "electra-base-japanese-discriminator", - "downloads": 42, + "downloads": 37, "source": "Hugging Face", - "score": -0.11378602049404264, + "score": -0.09240261940641396, "first_commit": "2021-11-15 17:39:41", "latest_commit": "2022-12-09 00:43:19", "languages": [], @@ -10030,166 +10425,138 @@ "model_architectures": "ElectraForPreTraining" }, { - "description": "Japanese to Korean translator Japanese to Korean translator model based on EncoderDecoderModel(bert-japanese+kogpt2)", - "url": "https://huggingface.co/sappho192/aihub-ja-ko-translator", - "project_name": "aihub-ja-ko-translator", - "downloads": 42, + "description": "This is a BERT Base model for emotion analysis in Japanese additionally fine-tuned for emotion detection and classification.", + "url": "https://huggingface.co/alter-wang/bert-base-japanese-emotion-lily", + "project_name": "bert-base-japanese-emotion-lily", + "downloads": 37, "source": "Hugging Face", - "score": -0.11378602049404264, - "first_commit": "2024-02-05 00:51:47", - "latest_commit": "2024-06-28 06:38:39", + "score": -0.09240261940641396, + "first_commit": "2024-04-25 06:05:51", + "latest_commit": "2024-06-17 01:44:16", "languages": [], "model_or_dataset": "model", - "model_size": 0.265, - "model_architectures": "EncoderDecoderModel" - }, - { - "description": "cosmopedia-100k のindex 20k ～ 100k を日本語に自動翻訳したデータになります（テキストが長すぎて翻訳エラーになったレコードは除外しています）。", - "url": "https://huggingface.co/datasets/kunishou/cosmopedia-100k-ja-preview", - "project_name": "cosmopedia-100k-ja-preview", - "downloads": 42, - "source": "Hugging Face", - "score": -0.11378602049404264, - "first_commit": "2024-02-28 07:58:55", - "latest_commit": "2024-03-05 23:30:38", - "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null + "model_size": 0.111, + "model_architectures": "BertForSequenceClassification" }, { - "description": "Heron BLIP Japanese StableLM", - "url": "https://huggingface.co/turing-motors/heron-chat-blip-ja-stablelm-base-7b-v1", - "project_name": "heron-chat-blip-ja-stablelm-base-7b-v1", - "downloads": 41, + "description": "This is a model for named entity recognition of Japanese medical documents.", + "url": "https://huggingface.co/sociocom/MedNERN-CR-JA", + "project_name": "MedNERN-CR-JA", + "downloads": 37, "source": "Hugging Face", - "score": -0.11380173185073686, - "first_commit": "2024-02-20 11:32:57", - "latest_commit": "2024-02-27 13:57:20", + "score": -0.09240261940641396, + "first_commit": "2023-04-13 08:25:56", + "latest_commit": "2024-02-26 13:53:06", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "VideoBlipForConditionalGeneration" + "model_size": 0.11, + "model_architectures": "BertForTokenClassification" }, { - "description": "Wikipedia日本語版データセット(izumi-lab/wikipedia-ja-20230720)", - "url": "https://huggingface.co/datasets/shi3z/Japanese_Wikipedia_Conversation", - "project_name": "Japanese_Wikipedia_Conversation", - "downloads": 41, + "description": "Miwa-Keita/zenz-v1-checkpoints を optimum 用に ONNX に変換したモデルです。", + "url": "https://huggingface.co/p1atdev/zenz-v1-onnx", + "project_name": "zenz-v1-onnx", + "downloads": 36, "source": "Hugging Face", - "score": -0.11380173185073686, - "first_commit": "2023-11-10 07:36:40", - "latest_commit": "2023-11-10 22:46:29", + "score": -0.09241322435695029, + "first_commit": "2024-06-29 03:03:03", + "latest_commit": "2024-06-29 03:40:34", "languages": [], - "model_or_dataset": "dataset", + "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "GPT2LMHeadModel" }, { - "description": "モデル ベースモデル：microsoft/Phi-3-mini-4k-instruct 学習データセット：llm-jp/hh-rlhf-12k-ja 学習方式：フルパラメータチューニング サンプル import torch from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained( \"ryota39/Phi-3-mini-4k-instruct-dpo\", trust_remote_code=True, ) model = AutoModelForCausalLM.from_pretrained( \"ryota39/Phi-3-mini-4k-instruct-dpo\", device_map=\"auto\", torch_dtype='auto', trust_remote_code=True, ) text = \"<|user|>\\n与えられた質問に対して英語で思考し、日本語で答えてください。", - "url": "https://huggingface.co/ryota39/Phi-3-mini-4k-instruct-dpo", - "project_name": "Phi-3-mini-4k-instruct-dpo", - "downloads": 40, + "description": "Japanese-LLaMA-2-13B-GGUF Japanese-LLaMA-2-13B-GGUFはJapanese-LLaMA-2-13BのGGUF形式です。 ", + "url": "https://huggingface.co/owner203/japanese-llama-2-13b-gguf", + "project_name": "japanese-llama-2-13b-gguf", + "downloads": 36, "source": "Hugging Face", - "score": -0.11381744320743108, - "first_commit": "2024-04-24 16:21:32", - "latest_commit": "2024-05-01 07:41:46", + "score": -0.09241322435695029, + "first_commit": "2023-12-20 05:37:09", + "latest_commit": "2023-12-26 11:45:15", "languages": [], "model_or_dataset": "model", - "model_size": 3.82, - "model_architectures": "Phi3ForCausalLM" + "model_size": 13.3, + "model_architectures": null }, { - "description": "line-corporation/japanese-large-lm-3.6b line-corporationさんが公開しているjapanese-large-lm-3.6bのgguf変換版です。 ", - "url": "https://huggingface.co/mmnga/line-corp-japanese-large-lm-3.6b-gguf", - "project_name": "line-corp-japanese-large-lm-3.6b-gguf", - "downloads": 40, + "description": "Dataset Summary SNOW T15:The simplified corpus for the Japanese language.", + "url": "https://huggingface.co/datasets/SNOW-NLP/snow_simplified_japanese_corpus", + "project_name": "snow_simplified_japanese_corpus", + "downloads": 36, "source": "Hugging Face", - "score": -0.11381744320743108, - "first_commit": "2023-09-02 18:18:41", - "latest_commit": "2023-09-08 02:53:05", + "score": -0.09241322435695029, + "first_commit": "2022-01-25 16:36:23", + "latest_commit": "2024-01-18 11:16:01", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "The English document is here. ", - "url": "https://huggingface.co/watashiha/Watashiha-Llama-2-13B-Ogiri-sft", - "project_name": "Watashiha-Llama-2-13B-Ogiri-sft", - "downloads": 40, - "source": "Hugging Face", - "score": -0.11381744320743108, - "first_commit": "2024-01-19 06:59:08", - "latest_commit": "2024-03-04 05:24:31", - "languages": [], - "model_or_dataset": "model", - "model_size": 13.1, - "model_architectures": "LlamaForCausalLM" - }, - { - "description": "bert-base-japanese-jsnli This model is a fine-tuned version of cl-tohoku/bert-base-japanese-v2 on the JSNLI dataset.", - "url": "https://huggingface.co/Formzu/bert-base-japanese-jsnli", - "project_name": "bert-base-japanese-jsnli", - "downloads": 39, + "description": "NVIDIA が公開している SteerLM 向けのトライアルデータセット HelpSteerを日本語に自動翻訳したデータセットになります。", + "url": "https://huggingface.co/datasets/kunishou/HelpSteer-35k-ja", + "project_name": "HelpSteer-35k-ja", + "downloads": 36, "source": "Hugging Face", - "score": -0.1138331545641253, - "first_commit": "2022-10-14 07:50:13", - "latest_commit": "2022-10-18 12:13:20", + "score": -0.09241322435695029, + "first_commit": "2024-03-02 16:45:19", + "latest_commit": "2024-03-03 10:10:54", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "BertForSequenceClassification" + "model_architectures": null }, { - "description": "llm-japanese-dataset-vanilla LLM構築用の日本語チャットデータセット izumi-lab/llm-japanese-dataset から，日英翻訳のデータセット等を抜いたものです． ", - "url": "https://huggingface.co/datasets/izumi-lab/llm-japanese-dataset-vanilla", - "project_name": "llm-japanese-dataset-vanilla", - "downloads": 39, + "description": "luke-large-defamation-detection-japanese 日本語誹謗中傷検出器", + "url": "https://huggingface.co/kubota/luke-large-defamation-detection-japanese", + "project_name": "luke-large-defamation-detection-japanese", + "downloads": 35, "source": "Hugging Face", - "score": -0.1138331545641253, - "first_commit": "2023-05-23 14:45:27", - "latest_commit": "2024-02-17 16:17:18", + "score": -0.09242382930748663, + "first_commit": "2023-01-23 06:25:08", + "latest_commit": "2023-02-07 15:49:33", "languages": [], - "model_or_dataset": "dataset", + "model_or_dataset": "model", "model_size": null, - "model_architectures": null - }, - { - "description": "cyberagent/calm2-7b-chatの出力を人手でチェック・修正することで作成した日本語Instructionデータセットです。 ", - "url": "https://huggingface.co/datasets/Kendamarron/jimba-instuction-1k-beta", - "project_name": "jimba-instuction-1k-beta", - "downloads": 38, + "model_architectures": "LukeForSequenceClassification" + }, + { + "description": "This is my conversion of NilanE/ParallelFiction-Ja_En-100k into json which can be read by text-generation-webui when training a model.", + "url": "https://huggingface.co/datasets/mpasila/ParallelFiction-Ja_En-100k-json", + "project_name": "ParallelFiction-Ja_En-100k-json", + "downloads": 35, "source": "Hugging Face", - "score": -0.11384886592081951, - "first_commit": "2024-02-29 15:23:48", - "latest_commit": "2024-04-25 12:49:28", + "score": -0.09242382930748663, + "first_commit": "2024-03-26 06:08:27", + "latest_commit": "2024-04-02 04:46:10", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "オリジナルのサイトと同じものを使用しています。 ", - "url": "https://huggingface.co/datasets/llm-book/ja-vicuna-qa-benchmark", - "project_name": "ja-vicuna-qa-benchmark", - "downloads": 38, + "description": "BERT large Japanese (character-level tokenization with whole word masking, jawiki-20200831)", + "url": "https://huggingface.co/tohoku-nlp/bert-large-japanese-char", + "project_name": "bert-large-japanese-char", + "downloads": 34, "source": "Hugging Face", - "score": -0.11384886592081951, - "first_commit": "2024-06-25 22:14:55", - "latest_commit": "2024-08-31 12:37:25", + "score": -0.09243443425802296, + "first_commit": "2021-03-05 06:36:24", + "latest_commit": "2021-09-23 15:45:39", "languages": [], - "model_or_dataset": "dataset", + "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "BertForMaskedLM" }, { "description": "yacis-electra-small-cyberbullying", "url": "https://huggingface.co/ptaszynski/yacis-electra-small-japanese-cyberbullying", "project_name": "yacis-electra-small-japanese-cyberbullying", - "downloads": 37, + "downloads": 34, "source": "Hugging Face", - "score": -0.11386457727751373, + "score": -0.09243443425802296, "first_commit": "2022-01-12 03:57:13", "latest_commit": "2022-01-16 13:51:28", "languages": [], @@ -10198,236 +10565,236 @@ "model_architectures": "ElectraForSequenceClassification" }, { - "description": "Sarashina2-7B Instruct sarashina2-7Bを会話できるようにフルファインチューニングしたものです。", - "url": "https://huggingface.co/alfredplpl/sarashina2-7b-it", - "project_name": "sarashina2-7b-it", - "downloads": 37, + "description": "Fine-tuned XLSR-53 large model for speech diarization in Japanese phone-call 2 speakers diarization model which was fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using phone-call data CallHome.", + "url": "https://huggingface.co/Ivydata/wav2vec2-large-speech-diarization-jp", + "project_name": "wav2vec2-large-speech-diarization-jp", + "downloads": 34, "source": "Hugging Face", - "score": -0.11386457727751373, - "first_commit": "2024-06-12 02:24:28", - "latest_commit": "2024-06-12 03:00:35", + "score": -0.09243443425802296, + "first_commit": "2023-05-08 10:10:43", + "latest_commit": "2023-05-10 00:32:23", "languages": [], "model_or_dataset": "model", - "model_size": 7.32, - "model_architectures": "LlamaForCausalLM" + "model_size": null, + "model_architectures": "Wav2Vec2ForAudioFrameClassification" }, { - "description": "Model trained on 800,000 Japanese sentences after reducing oshizo/japanese-e5-mistral-7b_slerp to 8 layers.", - "url": "https://huggingface.co/oshizo/japanese-e5-mistral-1.9b", - "project_name": "japanese-e5-mistral-1.9b", - "downloads": 37, + "description": "deberta-large-japanese-wikipedia-ud-head Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-wikipedia-ud-head", + "project_name": "deberta-large-japanese-wikipedia-ud-head", + "downloads": 33, "source": "Hugging Face", - "score": -0.11386457727751373, - "first_commit": "2024-02-02 12:39:11", - "latest_commit": "2024-02-03 00:28:28", + "score": -0.0924450392085593, + "first_commit": "2022-07-06 03:51:14", + "latest_commit": "2024-08-20 19:51:21", "languages": [], "model_or_dataset": "model", - "model_size": 1.88, - "model_architectures": "MistralForEmbedding" + "model_size": null, + "model_architectures": "DebertaV2ForQuestionAnswering" }, { - "description": "NVIDIA が公開している SteerLM 向けのトライアルデータセット HelpSteerを日本語に自動翻訳したデータセットになります。", - "url": "https://huggingface.co/datasets/kunishou/HelpSteer-35k-ja", - "project_name": "HelpSteer-35k-ja", - "downloads": 36, + "description": "Tanuki-8x8B-dpo-v1.0-GPTQ-8bit 概要 GENIAC 松尾研 LLM開発プロジェクトで開発されたLLMであるweblab-GENIAC/Tanuki-8x8B-dpo-v1.0のGPTQ 8bit量子化モデルです。", + "url": "https://huggingface.co/team-hatakeyama-phase2/Tanuki-8x8B-dpo-v1.0-GPTQ-8bit", + "project_name": "Tanuki-8x8B-dpo-v1.0-GPTQ-8bit", + "downloads": 33, "source": "Hugging Face", - "score": -0.11388028863420795, - "first_commit": "2024-03-02 16:45:19", - "latest_commit": "2024-03-03 10:10:54", + "score": -0.0924450392085593, + "first_commit": "2024-08-28 02:30:27", + "latest_commit": "2024-09-03 09:26:02", "languages": [], - "model_or_dataset": "dataset", + "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "TanukiForCausalLM" }, { - "description": "このモデルはluke-japanese-baseをファインチューニングして、MARC-ja(positive or negativeの二値分類)に用いれるようにしたものです。 ", - "url": "https://huggingface.co/Mizuiro-sakura/luke-japanese-base-marcja", - "project_name": "luke-japanese-base-marcja", - "downloads": 35, + "description": "deberta-small-japanese-upos Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-small-japanese-upos", + "project_name": "deberta-small-japanese-upos", + "downloads": 33, "source": "Hugging Face", - "score": -0.11389599999090216, - "first_commit": "2023-03-02 03:57:33", - "latest_commit": "2023-07-21 14:10:48", + "score": -0.0924450392085593, + "first_commit": "2022-05-23 23:55:56", + "latest_commit": "2024-07-26 15:38:41", "languages": [], "model_or_dataset": "model", - "model_size": 0.279, - "model_architectures": "LukeForSequenceClassification" + "model_size": null, + "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "つくよみちゃんデータセットを用いて calm-2-7b-chat をファインチューニングしたモデルです。", - "url": "https://huggingface.co/offtoung/tsukuyomi-chan-calm2-7b", - "project_name": "tsukuyomi-chan-calm2-7b", - "downloads": 35, + "description": "electra-base-cyberbullying This is a BERT Base model for the Japanese language finetuned for automatic cyberbullying detection.", + "url": "https://huggingface.co/kit-nlp/bert-base-japanese-basic-char-v2-cyberbullying", + "project_name": "bert-base-japanese-basic-char-v2-cyberbullying", + "downloads": 32, "source": "Hugging Face", - "score": -0.11389599999090216, - "first_commit": "2023-12-21 08:46:37", - "latest_commit": "2023-12-27 04:07:20", + "score": -0.09245564415909563, + "first_commit": "2022-09-08 09:09:39", + "latest_commit": "2022-11-01 07:20:52", "languages": [], "model_or_dataset": "model", - "model_size": 7.01, - "model_architectures": "LlamaForCausalLM" + "model_size": null, + "model_architectures": "BertForSequenceClassification" }, { - "description": "This is my conversion of NilanE/ParallelFiction-Ja_En-100k into json which can be read by text-generation-webui when training a model.", - "url": "https://huggingface.co/datasets/mpasila/ParallelFiction-Ja_En-100k-json", - "project_name": "ParallelFiction-Ja_En-100k-json", - "downloads": 35, + "description": "Yaki-Dofu-Mix 概要 / Overview Yaki-Dofu-Mix���、アニメ風の画風に特化したマージモデルです。 ", + "url": "https://huggingface.co/Vsukiyaki/Yaki-Dofu-Mix", + "project_name": "Yaki-Dofu-Mix", + "downloads": 32, "source": "Hugging Face", - "score": -0.11389599999090216, - "first_commit": "2024-03-26 06:08:27", - "latest_commit": "2024-04-02 04:46:10", + "score": -0.09245564415909563, + "first_commit": "2023-12-23 09:26:20", + "latest_commit": "2023-12-24 11:07:09", "languages": [], - "model_or_dataset": "dataset", + "model_or_dataset": "model", "model_size": null, "model_architectures": null }, { - "description": "Dataset overview This dataset identifies whether a GitHub repository description pertains to Japanese natural language processing (NLP).", - "url": "https://huggingface.co/datasets/taishi-i/awesome-japanese-nlp-classification-dataset", - "project_name": "awesome-japanese-nlp-classification-dataset", - "downloads": 35, + "description": "mathstral-7B-v0.1-gguf mistralaiさんが公開しているmathstral-7B-v0.1のggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/mathstral-7B-v0.1-gguf", + "project_name": "mathstral-7B-v0.1-gguf", + "downloads": 32, "source": "Hugging Face", - "score": -0.11389599999090216, - "first_commit": "2023-09-09 06:37:36", - "latest_commit": "2023-09-09 20:09:04", + "score": -0.09245564415909563, + "first_commit": "2024-07-17 17:49:56", + "latest_commit": "2024-07-17 18:54:27", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_or_dataset": "model", + "model_size": 7.25, "model_architectures": null }, { - "description": "Kokuwa lamettaの改良でマージさせるモデル探しをしていたらKiwiMixという面白そうなモデルを見つけました。 ", - "url": "https://huggingface.co/Lasorco/Kokuwa", - "project_name": "Kokuwa", - "downloads": 34, + "description": "Ruri-Reranker: Japanese General Reranker Usage Direct Usage (Sentence Transformers)", + "url": "https://huggingface.co/cl-nagoya/ruri-reranker-stage1-large", + "project_name": "ruri-reranker-stage1-large", + "downloads": 32, "source": "Hugging Face", - "score": -0.11391171134759638, - "first_commit": "2023-10-24 14:10:27", - "latest_commit": "2023-10-26 04:22:46", + "score": -0.09245564415909563, + "first_commit": "2024-08-19 23:48:54", + "latest_commit": "2024-09-04 08:54:05", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": null + "model_size": 0.337, + "model_architectures": "BertForSequenceClassification" }, { - "description": "English - Japanese pairs taken from https://tatoeba.org/en/downloads and then deduplicated.", - "url": "https://huggingface.co/datasets/Verah/tatoeba_dedupe_en-jp_2024-March-01", - "project_name": "tatoeba_dedupe_en-jp_2024-March-01", - "downloads": 34, + "description": "The English document is here. ", + "url": "https://huggingface.co/watashiha/Watashiha-Llama-2-13B-Ogiri-sft", + "project_name": "Watashiha-Llama-2-13B-Ogiri-sft", + "downloads": 32, "source": "Hugging Face", - "score": -0.11391171134759638, - "first_commit": "2024-03-05 13:46:13", - "latest_commit": "2024-03-06 08:34:02", + "score": -0.09245564415909563, + "first_commit": "2024-01-19 06:59:08", + "latest_commit": "2024-03-04 05:24:31", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null + "model_or_dataset": "model", + "model_size": 13.1, + "model_architectures": "LlamaForCausalLM" }, { - "description": "One more step before getting this model.", - "url": "https://huggingface.co/rinna/japanese-stable-diffusion", - "project_name": "japanese-stable-diffusion", - "downloads": 33, + "description": "You agree to the terms of the LICENSE when using this dataset. ", + "url": "https://huggingface.co/datasets/litagin/ehehe-corpus", + "project_name": "ehehe-corpus", + "downloads": 32, "source": "Hugging Face", - "score": -0.1139274227042906, + "score": -0.09245564415909563, "first_commit": null, "latest_commit": null, "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "COMET-T5 ja Finetuned T5 on ATOMIC ja using a text-to-text language modeling objective.", - "url": "https://huggingface.co/nlp-waseda/comet-t5-base-japanese", - "project_name": "comet-t5-base-japanese", - "downloads": 33, + "description": "Wikipediaを用いた日本語の固有表現抽出データセット GitHub: https://github.com/stockmarkteam/ner-wikipedia-dataset/ LICENSE: CC-BY-SA 3.0 Developed by Stockmark Inc.", + "url": "https://huggingface.co/datasets/stockmark/ner-wikipedia-dataset", + "project_name": "ner-wikipedia-dataset", + "downloads": 32, "source": "Hugging Face", - "score": -0.1139274227042906, - "first_commit": "2022-11-12 15:07:40", - "latest_commit": "2023-02-08 09:26:55", + "score": -0.09245564415909563, + "first_commit": "2023-09-02 14:38:55", + "latest_commit": "2023-09-02 14:42:18", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "T5ForConditionalGeneration" + "model_architectures": null }, { - "description": "モデル説明 (model explanation) V1 = MoeDiffusion 1.0 + (HassanBlend 1.5 - VMix03) * 0.2 V2 = MoeDiffusion 0.6 : HassanBlend 1.5 0.2 : VMix03 : 0.2 マージ元のルーツにNAIリークやInsta系モデルが含まれるという噂があるので、NAIリークアンチ・Insta系モデルアンチには非推奨 理想の黒髪ポニテ顔が出せるYaguruMagikuを、ある程度顔が近くて制御しやすいAbyssOrangeMix2と混ぜてみた。 ", - "url": "https://huggingface.co/ThePioneer/MoeDiffusionPlusPlus", - "project_name": "MoeDiffusionPlusPlus", - "downloads": 33, + "description": "deberta-base-japanese-unidic Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-unidic", + "project_name": "deberta-base-japanese-unidic", + "downloads": 31, "source": "Hugging Face", - "score": -0.1139274227042906, - "first_commit": "2023-01-19 13:04:02", - "latest_commit": "2023-01-21 02:05:54", + "score": -0.09246624910963197, + "first_commit": "2022-06-08 08:05:33", + "latest_commit": "2022-06-18 23:02:31", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "DebertaV2ForMaskedLM" }, { - "description": "bert-japanese_finetuned-sentiment-analysis This model was trained from scratch on the Japanese Sentiment Polarity Dictionary dataset.", - "url": "https://huggingface.co/minutillamolinara/bert-japanese_finetuned-sentiment-analysis", - "project_name": "bert-japanese_finetuned-sentiment-analysis", - "downloads": 33, + "description": "alabnii/jmedroberta-base-manbyo-wordpiece-vocab50000 Model description This is a Japanese RoBERTa base model pre-trained on academic articles in medical sciences collected by Japan Science and Technology Agency (JST).", + "url": "https://huggingface.co/alabnii/jmedroberta-base-manbyo-wordpiece-vocab50000", + "project_name": "jmedroberta-base-manbyo-wordpiece-vocab50000", + "downloads": 31, "source": "Hugging Face", - "score": -0.1139274227042906, - "first_commit": "2023-03-31 02:28:09", - "latest_commit": "2023-03-31 13:13:37", + "score": -0.09246624910963197, + "first_commit": "2022-12-22 17:19:15", + "latest_commit": "2023-03-08 01:47:12", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "BertForSequenceClassification" + "model_architectures": "BertForMaskedLM" }, { - "description": "Model card for model ID", - "url": "https://huggingface.co/retrieva-jp/t5-base-short", - "project_name": "t5-base-short", - "downloads": 33, + "description": "このモデルはdeberta-v2-base-japaneseをファインチューニングして固有表現抽出（NER）に用いれるようにしたものです。 ", + "url": "https://huggingface.co/Mizuiro-sakura/deberta-v2-base-japanese-finetuned-ner", + "project_name": "deberta-v2-base-japanese-finetuned-ner", + "downloads": 31, "source": "Hugging Face", - "score": -0.1139274227042906, - "first_commit": "2023-04-26 08:20:52", - "latest_commit": "2023-05-10 10:00:23", + "score": -0.09246624910963197, + "first_commit": "2023-01-20 05:57:37", + "latest_commit": "2023-03-27 08:05:06", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "T5ForConditionalGeneration" + "model_size": 0.112, + "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "nlp-waseda/bigbird-base-japanese Model description This is a Japanese BigBird base model pretrained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.", - "url": "https://huggingface.co/nlp-waseda/bigbird-base-japanese", - "project_name": "bigbird-base-japanese", - "downloads": 33, + "description": "Japanese-LLaMA-2-7B-GGUF Japanese-LLaMA-2-7B-GGUFはJapanese-LLaMA-2-7BのGGUF形式です。 ", + "url": "https://huggingface.co/owner203/japanese-llama-2-7b-gguf", + "project_name": "japanese-llama-2-7b-gguf", + "downloads": 31, "source": "Hugging Face", - "score": -0.1139274227042906, - "first_commit": "2023-06-03 12:51:12", - "latest_commit": "2023-06-20 10:49:17", + "score": -0.09246624910963197, + "first_commit": "2024-01-22 03:00:02", + "latest_commit": "2024-06-05 02:30:01", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BigBirdForMaskedLM" + "model_size": 6.97, + "model_architectures": null }, { - "description": "Swallow-8Bは追加の日本語継続事前学習により日本語が大変流暢なLlama-3派生モデルです。", - "url": "https://huggingface.co/aixsatoshi/Meta-Llama-3.1-8B-Instruct-plus-Swallow", - "project_name": "Meta-Llama-3.1-8B-Instruct-plus-Swallow", - "downloads": 33, + "description": "Mistral-Large-Instruct-2407-gguf mistralaiさんが公開しているMistral-Large-Instruct-2407のggufフォーマット変換版です。 ", + "url": "https://huggingface.co/mmnga/Mistral-Large-Instruct-2407-gguf", + "project_name": "Mistral-Large-Instruct-2407-gguf", + "downloads": 31, "source": "Hugging Face", - "score": -0.1139274227042906, - "first_commit": "2024-07-24 03:10:38", - "latest_commit": "2024-07-24 04:03:21", + "score": -0.09246624910963197, + "first_commit": "2024-07-24 18:59:58", + "latest_commit": "2024-07-26 12:21:45", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": "LlamaForCausalLM" + "model_size": 123.0, + "model_architectures": null }, { "description": "Japanese-LLaMA-3-8B-Instruct-v2-GGUF Japanese-LLaMA-3-8B-Instruct-v2-GGUFはJapanese-LLaMA-3-8B-Instruct-v2のGGUF形式です。 ", "url": "https://huggingface.co/owner203/japanese-llama-3-8b-instruct-v2-gguf", "project_name": "japanese-llama-3-8b-instruct-v2-gguf", - "downloads": 33, + "downloads": 31, "source": "Hugging Face", - "score": -0.1139274227042906, + "score": -0.09246624910963197, "first_commit": "2024-06-10 11:21:01", "latest_commit": "2024-06-21 06:35:03", "languages": [], @@ -10436,138 +10803,124 @@ "model_architectures": null }, { - "description": "japanese-gpt-1b-PII-masking Model Description japanese-gpt-1b-PII-masking は、 日本語事前学習済み1B GPTモデルをベースとして、日本語の文章から個人情報をマスキングするように学習したモデルです。 ", - "url": "https://huggingface.co/cameltech/japanese-gpt-1b-PII-masking", - "project_name": "japanese-gpt-1b-PII-masking", - "downloads": 33, + "description": "Deepreneur-blue-lizard Model Description Deepreneur-blue-lizardは、MetaのLlama-2-7bに対して、Wikipediaや書籍等の日本語の学習データを用いて追加事前学習と独自データによるファインチューニングを実施したモデルです。", + "url": "https://huggingface.co/Deepreneur/blue-lizard", + "project_name": "blue-lizard", + "downloads": 31, "source": "Hugging Face", - "score": -0.1139274227042906, - "first_commit": "2024-04-05 07:26:29", - "latest_commit": "2024-05-17 11:42:00", + "score": -0.09246624910963197, + "first_commit": "2024-02-05 16:29:48", + "latest_commit": "2024-02-12 14:43:33", "languages": [], "model_or_dataset": "model", - "model_size": 1.3, - "model_architectures": "GPT2LMHeadModel" + "model_size": 6.74, + "model_architectures": "LlamaForCausalLM" }, { - "description": "This dataset was created by automatically translating \"OpenAssistant/oasst1\" into Japanese.", - "url": "https://huggingface.co/datasets/kunishou/oasst1-89k-ja", - "project_name": "oasst1-89k-ja", - "downloads": 33, + "description": "Japanese-Alpaca-2-13B-GGUF Japanese-Alpaca-2-13B-GGUFはJapanese-Alpaca-2-13BのGGUF形式です。 ", + "url": "https://huggingface.co/owner203/japanese-alpaca-2-13b-gguf", + "project_name": "japanese-alpaca-2-13b-gguf", + "downloads": 31, "source": "Hugging Face", - "score": -0.1139274227042906, - "first_commit": "2023-05-06 09:12:30", - "latest_commit": "2024-04-01 17:15:31", + "score": -0.09246624910963197, + "first_commit": "2023-12-20 10:56:08", + "latest_commit": "2023-12-26 11:46:41", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_or_dataset": "model", + "model_size": 13.3, "model_architectures": null }, { - "description": "electra-base-cyberbullying This is a BERT Base model for the Japanese language finetuned for automatic cyberbullying detection.", - "url": "https://huggingface.co/kit-nlp/bert-base-japanese-basic-char-v2-cyberbullying", - "project_name": "bert-base-japanese-basic-char-v2-cyberbullying", - "downloads": 32, + "description": "deberta-large-japanese-wikipedia-ud-goeswith Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-wikipedia-ud-goeswith", + "project_name": "deberta-large-japanese-wikipedia-ud-goeswith", + "downloads": 31, "source": "Hugging Face", - "score": -0.11394313406098482, - "first_commit": "2022-09-08 09:09:39", - "latest_commit": "2022-11-01 07:20:52", + "score": -0.09246624910963197, + "first_commit": "2022-09-18 08:41:06", + "latest_commit": "2023-05-12 01:29:13", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "BertForSequenceClassification" + "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "This is a BERT Base model for emotion analysis in Japanese additionally fine-tuned for emotion detection and classification.", - "url": "https://huggingface.co/alter-wang/bert-base-japanese-emotion-lily", - "project_name": "bert-base-japanese-emotion-lily", - "downloads": 32, + "description": "deberta-base-japanese-aozora Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-aozora", + "project_name": "deberta-base-japanese-aozora", + "downloads": 31, "source": "Hugging Face", - "score": -0.11394313406098482, - "first_commit": "2024-04-25 06:05:51", - "latest_commit": "2024-06-17 01:44:16", + "score": -0.09246624910963197, + "first_commit": "2022-05-24 04:30:28", + "latest_commit": "2023-01-08 08:41:04", "languages": [], "model_or_dataset": "model", - "model_size": 0.111, - "model_architectures": "BertForSequenceClassification" + "model_size": null, + "model_architectures": "DebertaV2ForMaskedLM" }, { - "description": "Mixtral-8x7B-Instruct-v0.1-japanese-alpha-merged Mixtral-8x7B-Instruct-v0.1-japanese-alpha-mergedはMixtral-8x7B-Instruct-v0.1をベースに日本語の語彙拡張継続事前学習を実施した学習途中のモデルに対して、差分マージを実施したモデルです。", - "url": "https://huggingface.co/abeja/Mixtral-8x7B-Instruct-v0.1-japanese-alpha-merged", - "project_name": "Mixtral-8x7B-Instruct-v0.1-japanese-alpha-merged", - "downloads": 32, + "description": "deberta-base-japanese-juman-ud-goeswith Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-juman-ud-goeswith", + "project_name": "deberta-base-japanese-juman-ud-goeswith", + "downloads": 30, "source": "Hugging Face", - "score": -0.11394313406098482, - "first_commit": "2024-04-16 07:54:14", - "latest_commit": "2024-04-20 09:14:59", + "score": -0.0924768540601683, + "first_commit": "2023-02-05 06:48:32", + "latest_commit": "2023-05-12 01:16:53", "languages": [], "model_or_dataset": "model", - "model_size": 46.9, - "model_architectures": "MixtralForCausalLM" + "model_size": null, + "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "This is a little bit different version of kunishou/hh-rlhf-49k-ja without ng_translation == 1 examples.", - "url": "https://huggingface.co/datasets/fujiki/japanese_hh-rlhf-49k", - "project_name": "japanese_hh-rlhf-49k", - "downloads": 32, + "description": "This dataset was created by automatically translating \"OpenAssistant/oasst1\" into Japanese.", + "url": "https://huggingface.co/datasets/kunishou/oasst1-89k-ja", + "project_name": "oasst1-89k-ja", + "downloads": 30, "source": "Hugging Face", - "score": -0.11394313406098482, - "first_commit": "2023-05-28 05:55:53", - "latest_commit": "2023-05-28 06:08:04", + "score": -0.0924768540601683, + "first_commit": "2023-05-06 09:12:30", + "latest_commit": "2024-04-01 17:15:31", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "alabnii/jmedroberta-base-manbyo-wordpiece-vocab50000 Model description This is a Japanese RoBERTa base model pre-trained on academic articles in medical sciences collected by Japan Science and Technology Agency (JST).", - "url": "https://huggingface.co/alabnii/jmedroberta-base-manbyo-wordpiece-vocab50000", - "project_name": "jmedroberta-base-manbyo-wordpiece-vocab50000", - "downloads": 31, + "description": "deberta-large-japanese-upos Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-upos", + "project_name": "deberta-large-japanese-upos", + "downloads": 29, "source": "Hugging Face", - "score": -0.11395884541767903, - "first_commit": "2022-12-22 17:19:15", - "latest_commit": "2023-03-08 01:47:12", + "score": -0.09248745901070464, + "first_commit": "2022-05-27 06:50:55", + "latest_commit": "2024-07-26 16:00:59", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "BertForMaskedLM" - }, - { - "description": "rinna/nekomata-14b-gguf Overview The model is the GGUF version of rinna/nekomata-14b.", - "url": "https://huggingface.co/rinna/nekomata-14b-gguf", - "project_name": "nekomata-14b-gguf", - "downloads": 31, - "source": "Hugging Face", - "score": -0.11395884541767903, - "first_commit": "2023-12-19 08:11:51", - "latest_commit": "2024-07-20 08:29:58", - "languages": [], - "model_or_dataset": "model", - "model_size": 14.2, - "model_architectures": null + "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "deberta-base-japanese-juman-ud-goeswith Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-juman-ud-goeswith", - "project_name": "deberta-base-japanese-juman-ud-goeswith", - "downloads": 30, + "description": "roberta-base-japanese-juman-ud-goeswith Model Description", + "url": "https://huggingface.co/KoichiYasuoka/roberta-base-japanese-juman-ud-goeswith", + "project_name": "roberta-base-japanese-juman-ud-goeswith", + "downloads": 29, "source": "Hugging Face", - "score": -0.11397455677437325, - "first_commit": "2023-02-05 06:48:32", - "latest_commit": "2023-05-12 01:16:53", + "score": -0.09248745901070464, + "first_commit": "2023-02-21 03:43:52", + "latest_commit": "2024-08-30 14:46:25", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForTokenClassification" + "model_architectures": "RobertaForTokenClassification" }, { "description": "Orion-14B 🌐English | 🇨", "url": "https://huggingface.co/OrionStarAI/Orion-14B-LongChat", "project_name": "Orion-14B-LongChat", - "downloads": 30, + "downloads": 29, "source": "Hugging Face", - "score": -0.11397455677437325, + "score": -0.09248745901070464, "first_commit": "2024-01-19 07:15:36", "latest_commit": "2024-03-26 10:10:34", "languages": [], @@ -10576,88 +10929,74 @@ "model_architectures": "OrionForCausalLM" }, { - "description": "jpn-heb source group: Japanese target group:", - "url": "https://huggingface.co/Helsinki-NLP/opus-mt-ja-he", - "project_name": "opus-mt-ja-he", - "downloads": 30, + "description": "SambaLingo-Japanese-Chat SambaLingo-Japanese-Chat is a human aligned chat model trained in Japanese and English.", + "url": "https://huggingface.co/sambanovasystems/SambaLingo-Japanese-Chat", + "project_name": "SambaLingo-Japanese-Chat", + "downloads": 29, "source": "Hugging Face", - "score": -0.11397455677437325, - "first_commit": "2020-08-19 00:28:58", - "latest_commit": "2023-08-16 11:59:12", + "score": -0.09248745901070464, + "first_commit": "2024-02-15 22:45:08", + "latest_commit": "2024-04-16 22:32:15", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "MarianMTModel" + "model_size": 6.95, + "model_architectures": "LlamaForCausalLM" }, { - "description": "ShareGPT-Processed The RyokoAI/ShareGPT52K dataset, converted to Markdown and labeled with the language used.", - "url": "https://huggingface.co/datasets/zetavg/ShareGPT-Processed", - "project_name": "ShareGPT-Processed", - "downloads": 30, + "description": "deberta-base-japanese-wikipedia-ud-head Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-wikipedia-ud-head", + "project_name": "deberta-base-japanese-wikipedia-ud-head", + "downloads": 29, "source": "Hugging Face", - "score": -0.11397455677437325, - "first_commit": "2023-05-16 19:50:04", - "latest_commit": "2023-05-21 03:50:14", + "score": -0.09248745901070464, + "first_commit": "2022-06-25 13:03:09", + "latest_commit": "2024-08-20 19:47:27", "languages": [], - "model_or_dataset": "dataset", + "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "DebertaV2ForQuestionAnswering" }, { - "description": "日本語ByT5事前学習済みモデル This is a ByT5 (a tokenizer-free extension of the Text-to-Text Transfer Transformer) model pretrained on Japanese corpus. ", - "url": "https://huggingface.co/sonoisa/byt5-small-japanese", - "project_name": "byt5-small-japanese", - "downloads": 29, + "description": "モデル説明 (model explanation) V1 = MoeDiffusion 1.0 + (HassanBlend 1.5 - VMix03) * 0.2 V2 = MoeDiffusion 0.6 : HassanBlend 1.5 0.2 : VMix03 : 0.2 マージ元のルーツにNAIリークやInsta系モデルが含まれるという噂があるので、NAIリークアンチ・Insta系モデルアンチには非推奨 理想の黒髪ポニテ顔が出せるYaguruMagikuを、ある程度顔が近くて制御しやすいAbyssOrangeMix2と混ぜてみた。 ", + "url": "https://huggingface.co/ThePioneer/MoeDiffusionPlusPlus", + "project_name": "MoeDiffusionPlusPlus", + "downloads": 28, "source": "Hugging Face", - "score": -0.11399026813106747, - "first_commit": "2021-06-04 13:14:22", - "latest_commit": "2021-09-23 18:29:53", + "score": -0.09249806396124097, + "first_commit": "2023-01-19 13:04:02", + "latest_commit": "2023-01-21 02:05:54", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "MT5ForConditionGeneration" + "model_architectures": null }, { - "description": "nlp-waseda/gpt2-xl-japanese This is Japanese GPT2 with approximately 1.5B parameters pretrained on Japanese Wikipedia and CC-100", - "url": "https://huggingface.co/nlp-waseda/gpt2-xl-japanese", - "project_name": "gpt2-xl-japanese", - "downloads": 29, + "description": "japanese-gpt-1b-PII-masking Model Description japanese-gpt-1b-PII-masking は、 日本語事前学習済み1B GPTモデルをベースとして、日本語の文章から個人情報をマスキングするように学習したモデルです。 ", + "url": "https://huggingface.co/cameltech/japanese-gpt-1b-PII-masking", + "project_name": "japanese-gpt-1b-PII-masking", + "downloads": 28, "source": "Hugging Face", - "score": -0.11399026813106747, - "first_commit": "2022-11-30 04:33:31", - "latest_commit": "2023-06-21 04:29:10", + "score": -0.09249806396124097, + "first_commit": "2024-04-05 07:26:29", + "latest_commit": "2024-05-17 11:42:00", "languages": [], "model_or_dataset": "model", - "model_size": 1.61, + "model_size": 1.3, "model_architectures": "GPT2LMHeadModel" }, { - "description": "This is a model for named entity recognition of Japanese medical documents.", - "url": "https://huggingface.co/sociocom/MedNERN-CR-JA", - "project_name": "MedNERN-CR-JA", - "downloads": 29, + "description": "Mixtral-8x7B-Instruct-v0.1-japanese-alpha-merged Mixtral-8x7B-Instruct-v0.1-japanese-alpha-mergedはMixtral-8x7B-Instruct-v0.1をベースに日本語の語彙拡張継続事前学習を実施した学習途中のモデルに対して、差分マージを実施したモデルです。", + "url": "https://huggingface.co/abeja/Mixtral-8x7B-Instruct-v0.1-japanese-alpha-merged", + "project_name": "Mixtral-8x7B-Instruct-v0.1-japanese-alpha-merged", + "downloads": 28, "source": "Hugging Face", - "score": -0.11399026813106747, - "first_commit": "2023-04-13 08:25:56", - "latest_commit": "2024-02-26 13:53:06", + "score": -0.09249806396124097, + "first_commit": "2024-04-16 07:54:14", + "latest_commit": "2024-04-20 09:14:59", "languages": [], "model_or_dataset": "model", - "model_size": 0.11, - "model_architectures": "BertForTokenClassification" - }, - { - "description": "Dataset Details Dataset Type:Japanese LLaVA v1.5", - "url": "https://huggingface.co/datasets/turing-motors/LLaVA-v1.5-Instruct-620K-JA", - "project_name": "LLaVA-v1.5-Instruct-620K-JA", - "downloads": 29, - "source": "Hugging Face", - "score": -0.11399026813106747, - "first_commit": "2024-04-10 05:04:58", - "latest_commit": "2024-04-12 09:18:42", - "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null + "model_size": 46.9, + "model_architectures": "MixtralForCausalLM" }, { "description": "mlx-community/Llama-3.1-70B-Japanese-Instruct-2407-4bit", @@ -10665,7 +11004,7 @@ "project_name": "Llama-3.1-70B-Japanese-Instruct-2407-4bit", "downloads": 28, "source": "Hugging Face", - "score": -0.11400597948776167, + "score": -0.09249806396124097, "first_commit": "2024-07-26 21:06:54", "latest_commit": "2024-07-26 21:37:02", "languages": [], @@ -10674,158 +11013,172 @@ "model_architectures": "LlamaForCausalLM" }, { - "description": "Tanuki-8x8B-dpo-v1.0-GPTQ-8bit 概要 GENIAC 松尾研 LLM開発プロジェクトで開発されたLLMであるweblab-GENIAC/Tanuki-8x8B-dpo-v1.0のGPTQ 8bit量子化モデルです。", - "url": "https://huggingface.co/team-hatakeyama-phase2/Tanuki-8x8B-dpo-v1.0-GPTQ-8bit", - "project_name": "Tanuki-8x8B-dpo-v1.0-GPTQ-8bit", + "description": "Ruri-Reranker: Japanese General Reranker Usage Direct Usage (Sentence Transformers)", + "url": "https://huggingface.co/cl-nagoya/ruri-reranker-stage1-small", + "project_name": "ruri-reranker-stage1-small", "downloads": 28, "source": "Hugging Face", - "score": -0.11400597948776167, - "first_commit": "2024-08-28 02:30:27", - "latest_commit": "2024-09-03 09:26:02", + "score": -0.09249806396124097, + "first_commit": "2024-08-19 09:44:00", + "latest_commit": "2024-09-04 08:53:02", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "TanukiForCausalLM" + "model_size": 0.06870000000000001, + "model_architectures": "DistilBertForSequenceClassification" }, { - "description": "luke-large-defamation-detection-japanese 日本語誹謗中傷検出器", - "url": "https://huggingface.co/kubota/luke-large-defamation-detection-japanese", - "project_name": "luke-large-defamation-detection-japanese", + "description": "deberta-base-japanese-unidic-ud-head Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-unidic-ud-head", + "project_name": "deberta-base-japanese-unidic-ud-head", "downloads": 28, "source": "Hugging Face", - "score": -0.11400597948776167, - "first_commit": "2023-01-23 06:25:08", - "latest_commit": "2023-02-07 15:49:33", + "score": -0.09249806396124097, + "first_commit": "2022-06-18 10:20:24", + "latest_commit": "2024-08-20 20:09:13", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "LukeForSequenceClassification" + "model_architectures": "DebertaV2ForQuestionAnswering" }, { - "description": "GPT-Neo 1.3B pre-trained model for Japanese Model Description GPT2/GPT3 like model trained on Japanese.corpus.", - "url": "https://huggingface.co/yellowback/gpt-neo-japanese-1.3B", - "project_name": "gpt-neo-japanese-1.3B", - "downloads": 27, + "description": "Kendamarron/jimba-wiki-instruction-calm3 grapevine-AI/CALM3-22B-Chat-GGUFのQ4_K_Mを使った合成instructionデータセットです。 ", + "url": "https://huggingface.co/datasets/Kendamarron/jimba-wiki-instruction-calm3", + "project_name": "jimba-wiki-instruction-calm3", + "downloads": 28, "source": "Hugging Face", - "score": -0.11402169084445589, - "first_commit": "2021-12-09 08:09:40", - "latest_commit": "2021-12-09 17:59:05", + "score": -0.09249806396124097, + "first_commit": "2024-07-09 22:18:35", + "latest_commit": "2024-07-20 12:57:05", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "GPTNeoForCausalLM" + "model_architectures": null }, { - "description": "Model Card for Japanese character-level GPT-2 Large Model description", - "url": "https://huggingface.co/ku-nlp/gpt2-large-japanese-char", - "project_name": "gpt2-large-japanese-char", + "description": "Synthetic-JP-Conversations-Magpie-Nemotron-4-10k Magpieの手法をnvidia/Nemotron-4-340B-Instructに対して適用し作成した、約10000件の日本語instruction tuning用データセットです。 ", + "url": "https://huggingface.co/datasets/Aratako/Synthetic-JP-Conversations-Magpie-Nemotron-4-10k", + "project_name": "Synthetic-JP-Conversations-Magpie-Nemotron-4-10k", + "downloads": 28, + "source": "Hugging Face", + "score": -0.09249806396124097, + "first_commit": "2024-07-05 13:53:45", + "latest_commit": "2024-07-05 13:57:08", + "languages": [], + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null + }, + { + "description": "Summary This is a text classifier for assigning a JLPT level.", + "url": "https://huggingface.co/bennexx/cl-tohoku-bert-base-japanese-v3-jlpt-classifier", + "project_name": "cl-tohoku-bert-base-japanese-v3-jlpt-classifier", "downloads": 27, "source": "Hugging Face", - "score": -0.11402169084445589, - "first_commit": "2023-12-27 11:18:45", - "latest_commit": "2023-12-27 12:07:30", + "score": -0.0925086689117773, + "first_commit": "2024-01-19 00:32:15", + "latest_commit": "2024-07-10 13:41:08", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "GPT2LMHeadModel" + "model_architectures": "BertForSequenceClassification" }, { - "description": "モデルの説明(English explanation is below.", - "url": "https://huggingface.co/keitokei1994/Llama-3-Umievo-Shizuko-sqlcoder-2x8B", - "project_name": "Llama-3-Umievo-Shizuko-sqlcoder-2x8B", + "description": "alabnii/jmedroberta-base-sentencepiece-vocab50000 Model description This is a Japanese RoBERTa base model pre-trained on academic articles in medical sciences collected by Japan Science and Technology Agency (JST).", + "url": "https://huggingface.co/alabnii/jmedroberta-base-sentencepiece-vocab50000", + "project_name": "jmedroberta-base-sentencepiece-vocab50000", "downloads": 27, "source": "Hugging Face", - "score": -0.11402169084445589, - "first_commit": "2024-06-09 12:17:00", - "latest_commit": "2024-06-11 07:39:45", + "score": -0.0925086689117773, + "first_commit": "2022-12-22 17:22:14", + "latest_commit": "2023-06-27 03:44:17", "languages": [], "model_or_dataset": "model", - "model_size": 13.7, - "model_architectures": "MixtralForCausalLM" + "model_size": 0.124, + "model_architectures": "BertForMaskedLM" }, { - "description": "Synthetic-JP-Conversations-Magpie-Nemotron-4-10k Magpieの手法をnvidia/Nemotron-4-340B-Instructに対して適用し作成した、約10000件の日本語instruction tuning用データセットです。 ", - "url": "https://huggingface.co/datasets/Aratako/Synthetic-JP-Conversations-Magpie-Nemotron-4-10k", - "project_name": "Synthetic-JP-Conversations-Magpie-Nemotron-4-10k", + "description": "モデル ベースモデル：microsoft/Phi-3-mini-4k-instruct 学習データセット：llm-jp/hh-rlhf-12k-ja 学習方式：フルパラメータチューニング サンプル import torch from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained( \"ryota39/Phi-3-mini-4k-instruct-dpo\", trust_remote_code=True, ) model = AutoModelForCausalLM.from_pretrained( \"ryota39/Phi-3-mini-4k-instruct-dpo\", device_map=\"auto\", torch_dtype='auto', trust_remote_code=True, ) text = \"<|user|>\\n与えられた質問に対して英語で思考し、日本語で答えてください。", + "url": "https://huggingface.co/ryota39/Phi-3-mini-4k-instruct-dpo", + "project_name": "Phi-3-mini-4k-instruct-dpo", "downloads": 27, "source": "Hugging Face", - "score": -0.11402169084445589, - "first_commit": "2024-07-05 13:53:45", - "latest_commit": "2024-07-05 13:57:08", + "score": -0.0925086689117773, + "first_commit": "2024-04-24 16:21:32", + "latest_commit": "2024-05-01 07:41:46", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null + "model_or_dataset": "model", + "model_size": 3.82, + "model_architectures": "Phi3ForCausalLM" }, { - "description": "読み込み方 from datasets import load_dataset dataset = load_dataset(\"YANS-official/ogiri-debug\", split=\"test\") 概要 大喜利生成の動作確認用データセットです。", - "url": "https://huggingface.co/datasets/YANS-official/ogiri-debug", - "project_name": "ogiri-debug", + "description": "Heron BLIP Japanese StableLM", + "url": "https://huggingface.co/turing-motors/heron-chat-blip-ja-stablelm-base-7b-v0", + "project_name": "heron-chat-blip-ja-stablelm-base-7b-v0", "downloads": 27, "source": "Hugging Face", - "score": -0.11402169084445589, - "first_commit": "2024-08-30 04:18:35", - "latest_commit": "2024-08-30 14:52:03", + "score": -0.0925086689117773, + "first_commit": "2023-09-06 09:31:44", + "latest_commit": "2023-09-07 16:59:14", "languages": [], - "model_or_dataset": "dataset", + "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "VideoBlipForConditionalGeneration" }, { - "description": "deberta-large-japanese-wikipedia-luw-upos Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-wikipedia-luw-upos", - "project_name": "deberta-large-japanese-wikipedia-luw-upos", - "downloads": 26, + "description": "日本語ByT5事前学習済みモデル This is a ByT5 (a tokenizer-free extension of the Text-to-Text Transfer Transformer) model pretrained on Japanese corpus. ", + "url": "https://huggingface.co/sonoisa/byt5-small-japanese", + "project_name": "byt5-small-japanese", + "downloads": 27, "source": "Hugging Face", - "score": -0.1140374022011501, - "first_commit": "2022-07-06 03:15:12", - "latest_commit": "2024-08-20 17:54:58", + "score": -0.0925086689117773, + "first_commit": "2021-06-04 13:14:22", + "latest_commit": "2021-09-23 18:29:53", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForTokenClassification" + "model_architectures": "MT5ForConditionGeneration" }, { - "description": "nlp-waseda/roberta-large-japanese-with-auto-jumanpp Model description", - "url": "https://huggingface.co/nlp-waseda/roberta-large-japanese-with-auto-jumanpp", - "project_name": "roberta-large-japanese-with-auto-jumanpp", + "description": "deberta-base-japanese-aozora-ud-goeswith Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-aozora-ud-goeswith", + "project_name": "deberta-base-japanese-aozora-ud-goeswith", "downloads": 26, "source": "Hugging Face", - "score": -0.1140374022011501, - "first_commit": "2022-10-15 05:40:40", - "latest_commit": "2022-10-21 15:55:27", + "score": -0.09251927386231364, + "first_commit": "2022-10-14 09:43:58", + "latest_commit": "2024-08-20 18:52:19", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "RobertaForMaskedLM" + "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "Deepreneur-blue-lizard Model Description Deepreneur-blue-lizardは、MetaのLlama-2-7bに対して、Wikipediaや書籍等の日本語の学習データを用いて追加事前学習と独自データによるファインチューニングを実施したモデルです。", - "url": "https://huggingface.co/Deepreneur/blue-lizard", - "project_name": "blue-lizard", + "description": "Swallow-8Bは追加の日本語継続事前学習により日本語が大変流暢なLlama-3派生モデルです。", + "url": "https://huggingface.co/aixsatoshi/Meta-Llama-3.1-8B-Instruct-plus-Swallow", + "project_name": "Meta-Llama-3.1-8B-Instruct-plus-Swallow", "downloads": 26, "source": "Hugging Face", - "score": -0.1140374022011501, - "first_commit": "2024-02-05 16:29:48", - "latest_commit": "2024-02-12 14:43:33", + "score": -0.09251927386231364, + "first_commit": "2024-07-24 03:10:38", + "latest_commit": "2024-07-24 04:03:21", "languages": [], "model_or_dataset": "model", - "model_size": 6.74, + "model_size": 8.03, "model_architectures": "LlamaForCausalLM" }, { - "description": "Mistral-Large-Instruct-2407-gguf mistralaiさんが公開しているMistral-Large-Instruct-2407のggufフォーマット変換版です。 ", - "url": "https://huggingface.co/mmnga/Mistral-Large-Instruct-2407-gguf", - "project_name": "Mistral-Large-Instruct-2407-gguf", + "description": "Tanuki-8B-dpo-v1.0-GPTQ-4bit 概要 GENIAC 松尾研 LLM開発プロジェクトで開発されたLLMであるweblab-GENIAC/Tanuki-8B-dpo-v1.0のGPTQ 4bit量子化モデルです。", + "url": "https://huggingface.co/team-hatakeyama-phase2/Tanuki-8B-dpo-v1.0-GPTQ-4bit", + "project_name": "Tanuki-8B-dpo-v1.0-GPTQ-4bit", "downloads": 26, "source": "Hugging Face", - "score": -0.1140374022011501, - "first_commit": "2024-07-24 18:59:58", - "latest_commit": "2024-07-26 12:21:45", + "score": -0.09251927386231364, + "first_commit": "2024-08-27 16:17:17", + "latest_commit": "2024-09-03 09:29:10", "languages": [], "model_or_dataset": "model", - "model_size": 123.0, - "model_architectures": null + "model_size": null, + "model_architectures": "LlamaForCausalLM" }, { "description": "データセットについて オープンソースLLMの出力を人手でチェック・修正したinstructionにSwallow-MXでoutputを生成したデータセットです。 ", @@ -10833,7 +11186,7 @@ "project_name": "pret-a-porter-instruction-v0.1", "downloads": 26, "source": "Hugging Face", - "score": -0.1140374022011501, + "score": -0.09251927386231364, "first_commit": "2024-03-26 13:08:14", "latest_commit": "2024-04-01 04:30:44", "languages": [], @@ -10842,270 +11195,298 @@ "model_architectures": null }, { - "description": "BERT large Japanese (character-level tokenization with whole word masking, jawiki-20200831)", - "url": "https://huggingface.co/tohoku-nlp/bert-large-japanese-char", - "project_name": "bert-large-japanese-char", - "downloads": 25, + "description": "固有表現ラベルはllm-book/ner-wikipedia-datasetと同様のものを採用しており、全部で8��類 (人名、法人名、地名、製品名、政治的組織名、施設名、その他の組織名、イベント名)あります。 ", + "url": "https://huggingface.co/datasets/llm-book/ner-wikinews-dataset", + "project_name": "ner-wikinews-dataset", + "downloads": 26, "source": "Hugging Face", - "score": -0.11405311355784432, - "first_commit": "2021-03-05 06:36:24", - "latest_commit": "2021-09-23 15:45:39", + "score": -0.09251927386231364, + "first_commit": "2023-04-22 14:32:21", + "latest_commit": "2023-12-12 11:22:26", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "BertForMaskedLM" + "model_architectures": null }, { - "description": "t5-base-xlsum-ja", - "url": "https://huggingface.co/p1atdev/t5-base-xlsum-ja", - "project_name": "t5-base-xlsum-ja", + "description": "llm-japanese-dataset-vanilla LLM構築用の日本語チャットデータセット izumi-lab/llm-japanese-dataset から，日英翻訳のデータセット等を抜いたものです． ", + "url": "https://huggingface.co/datasets/izumi-lab/llm-japanese-dataset-vanilla", + "project_name": "llm-japanese-dataset-vanilla", + "downloads": 26, + "source": "Hugging Face", + "score": -0.09251927386231364, + "first_commit": "2023-05-23 14:45:27", + "latest_commit": "2024-02-17 16:17:18", + "languages": [], + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null + }, + { + "description": "roberta-base-japanese-aozora-ud-goeswith Model Description", + "url": "https://huggingface.co/KoichiYasuoka/roberta-base-japanese-aozora-ud-goeswith", + "project_name": "roberta-base-japanese-aozora-ud-goeswith", "downloads": 25, "source": "Hugging Face", - "score": -0.11405311355784432, - "first_commit": "2023-10-06 03:18:28", - "latest_commit": "2023-11-20 09:25:16", + "score": -0.09252987881284996, + "first_commit": "2022-10-15 04:01:29", + "latest_commit": "2024-08-20 18:49:41", "languages": [], "model_or_dataset": "model", - "model_size": 0.248, - "model_architectures": "T5ForConditionalGeneration" + "model_size": null, + "model_architectures": "RobertaForTokenClassification" }, { - "description": "HuggingFaceFW/fineweb-edu-classifierを再現するために、日本語データでtohoku-nlp/bert-base-japanese-v3を学習したモデルです。 ", - "url": "https://huggingface.co/Kendamarron/fineweb-edu-classifier-ja-v2", - "project_name": "fineweb-edu-classifier-ja-v2", + "description": "bart-base-japanese-news(base-sized model)", + "url": "https://huggingface.co/stockmark/bart-base-japanese-news", + "project_name": "bart-base-japanese-news", "downloads": 25, "source": "Hugging Face", - "score": -0.11405311355784432, - "first_commit": "2024-06-14 13:20:22", - "latest_commit": "2024-06-14 13:28:08", + "score": -0.09252987881284996, + "first_commit": "2023-01-20 04:23:07", + "latest_commit": "2023-12-08 03:39:50", "languages": [], "model_or_dataset": "model", - "model_size": 0.111, - "model_architectures": "BertForSequenceClassification" + "model_size": 0.125, + "model_architectures": "BartForConditionalGeneration" }, { - "description": "rinna/japanese-data2vec-audio-base Overview This is a Japanese data2vec Audio Base model trained by rinna Co.", - "url": "https://huggingface.co/rinna/japanese-data2vec-audio-base", - "project_name": "japanese-data2vec-audio-base", - "downloads": 25, + "description": "GPT-Neo 1.3B pre-trained model for Japanese Model Description GPT2/GPT3 like model trained on Japanese.corpus.", + "url": "https://huggingface.co/yellowback/gpt-neo-japanese-1.3B", + "project_name": "gpt-neo-japanese-1.3B", + "downloads": 24, "source": "Hugging Face", - "score": -0.11405311355784432, - "first_commit": "2024-03-05 10:32:32", - "latest_commit": "2024-07-22 08:12:56", + "score": -0.0925404837633863, + "first_commit": "2021-12-09 08:09:40", + "latest_commit": "2021-12-09 17:59:05", "languages": [], "model_or_dataset": "model", - "model_size": 0.0932, - "model_architectures": "Data2VecAudioModel" + "model_size": null, + "model_architectures": "GPTNeoForCausalLM" }, { - "description": "[Under Construction]", - "url": "https://huggingface.co/datasets/bclavie/mmarco-japanese-hard-negatives", - "project_name": "mmarco-japanese-hard-negatives", - "downloads": 25, + "description": "deberta-large-japanese-unidic Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-unidic", + "project_name": "deberta-large-japanese-unidic", + "downloads": 24, "source": "Hugging Face", - "score": -0.11405311355784432, - "first_commit": "2023-12-24 13:04:27", - "latest_commit": "2023-12-24 18:52:04", + "score": -0.0925404837633863, + "first_commit": "2022-06-10 12:49:12", + "latest_commit": "2022-06-19 09:15:35", "languages": [], - "model_or_dataset": "dataset", + "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "DebertaV2ForMaskedLM" }, { - "description": "Chat & support: TheBloke's Discord server Want to contribute?", - "url": "https://huggingface.co/TheBloke/japanese-stablelm-instruct-beta-70B-GPTQ", - "project_name": "japanese-stablelm-instruct-beta-70B-GPTQ", + "description": "t5-base-xlsum-ja", + "url": "https://huggingface.co/p1atdev/t5-base-xlsum-ja", + "project_name": "t5-base-xlsum-ja", "downloads": 24, "source": "Hugging Face", - "score": -0.11406882491453854, - "first_commit": "2023-11-02 15:45:24", - "latest_commit": "2023-11-02 20:04:07", + "score": -0.0925404837633863, + "first_commit": "2023-10-06 03:18:28", + "latest_commit": "2023-11-20 09:25:16", "languages": [], "model_or_dataset": "model", - "model_size": 9.1, - "model_architectures": "LlamaForCausalLM" + "model_size": 0.248, + "model_architectures": "T5ForConditionalGeneration" }, { - "description": "日本語医療固有表現抽出モデル 概要 ソーシャル・コンピューティング研究室さまより公開されているMedTxt-CRを用いて、alabniiさまより公開されているRoBERTaをfine-tuningした固有表現抽出モデルです。 ", - "url": "https://huggingface.co/daisaku-s/medtxt_ner_roberta", - "project_name": "medtxt_ner_roberta", + "description": "transformer-lm-japanese-0.1b", + "url": "https://huggingface.co/fukugawa/transformer-lm-japanese-0.1b", + "project_name": "transformer-lm-japanese-0.1b", "downloads": 24, "source": "Hugging Face", - "score": -0.11406882491453854, - "first_commit": "2023-02-13 10:48:22", - "latest_commit": "2023-02-15 13:43:48", + "score": -0.0925404837633863, + "first_commit": "2023-07-12 02:11:11", + "latest_commit": "2024-06-03 06:17:19", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "BertForTokenClassification" + "model_architectures": "TransformerLMForCausalLM" }, { - "description": "Summary This is a text classifier for assigning a JLPT level.", - "url": "https://huggingface.co/bennexx/cl-tohoku-bert-base-japanese-v3-jlpt-classifier", - "project_name": "cl-tohoku-bert-base-japanese-v3-jlpt-classifier", + "description": "deberta-large-japanese-unidic-ud-head Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-unidic-ud-head", + "project_name": "deberta-large-japanese-unidic-ud-head", "downloads": 24, "source": "Hugging Face", - "score": -0.11406882491453854, - "first_commit": "2024-01-19 00:32:15", - "latest_commit": "2024-07-10 13:41:08", + "score": -0.0925404837633863, + "first_commit": "2022-06-19 00:10:56", + "latest_commit": "2023-11-05 17:51:08", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "BertForSequenceClassification" + "model_architectures": "DebertaV2ForQuestionAnswering" }, { - "description": "Fine-tuned Japanese Whisper model for speech recognition using whisper-base Fine-tuned openai/whisper-base on Japanese using Common Voice, JVS and JSUT.", - "url": "https://huggingface.co/Ivydata/whisper-base-japanese", - "project_name": "whisper-base-japanese", - "downloads": 23, + "description": "roberta-base-japanese-aozora Model Description", + "url": "https://huggingface.co/KoichiYasuoka/roberta-base-japanese-aozora", + "project_name": "roberta-base-japanese-aozora", + "downloads": 24, "source": "Hugging Face", - "score": -0.11408453627123276, - "first_commit": "2023-05-17 04:36:41", - "latest_commit": "2023-06-08 00:17:50", + "score": -0.0925404837633863, + "first_commit": "2021-12-21 00:04:03", + "latest_commit": "2022-10-15 14:20:11", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "WhisperForConditionalGeneration" + "model_architectures": "RobertaForMaskedLM" }, { - "description": "rinna/nekomata-7b-instruction-gguf Overview The model is the GGUF version of rinna/nekomata-7b-instruction.", - "url": "https://huggingface.co/rinna/nekomata-7b-instruction-gguf", - "project_name": "nekomata-7b-instruction-gguf", + "description": "ShareGPT-Processed The RyokoAI/ShareGPT52K dataset, converted to Markdown and labeled with the language used.", + "url": "https://huggingface.co/datasets/zetavg/ShareGPT-Processed", + "project_name": "ShareGPT-Processed", + "downloads": 24, + "source": "Hugging Face", + "score": -0.0925404837633863, + "first_commit": "2023-05-16 19:50:04", + "latest_commit": "2023-05-21 03:50:14", + "languages": [], + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null + }, + { + "description": "Model Trained Using AutoNLP Problem type: Binary Classification Model ID: 59363 Validation Metrics Loss: 0.12651239335536957 Accuracy: 0.9532079853817648 Precision: 0.9729688278823665 Recall: 0.9744633462616643 AUC: 0.9717333684823413 F1: 0.9737155136027014 Usage You can use cURL to access this model: $ curl -X POST -H \"Authorization: Bearer YOUR_API_KEY\" -H \"Content-Type: application/json\" -d '{\"inputs\": \"I love AutoNLP\"}' https://api-inference.huggingface.co/models/abhishek/autonlp-japanese-sentiment-5936", + "url": "https://huggingface.co/abhishek/autonlp-japanese-sentiment-59363", + "project_name": "autonlp-japanese-sentiment-59363", "downloads": 23, "source": "Hugging Face", - "score": -0.11408453627123276, - "first_commit": "2023-12-19 08:11:08", - "latest_commit": "2024-07-20 08:38:34", + "score": -0.09255108871392263, + "first_commit": "2021-04-21 11:28:24", + "latest_commit": "2021-05-18 22:56:15", "languages": [], "model_or_dataset": "model", - "model_size": 7.72, - "model_architectures": null + "model_size": null, + "model_architectures": "BertForSequenceClassification" }, { - "description": "rinna/nekomata-7b-gguf Overview The model is the GGUF version of rinna/nekomata-7b.", - "url": "https://huggingface.co/rinna/nekomata-7b-gguf", - "project_name": "nekomata-7b-gguf", + "description": "モデル説明 (model explanation) YaguruMagiku 0.6 : AbyssOrangeMix2_sfw 0.4 マージ元のルーツにNAIリークが含まれるという噂があるので、NAIリークアンチには非推奨 理想の黒髪ポニテ顔が出せるYaguruMagikuを、ある程度顔が近くて制御しやすいAbyssOrangeMix2と混ぜてみた。 ", + "url": "https://huggingface.co/ThePioneer/MoeDiffusion", + "project_name": "MoeDiffusion", "downloads": 23, "source": "Hugging Face", - "score": -0.11408453627123276, - "first_commit": "2023-12-19 08:10:42", - "latest_commit": "2024-07-20 08:36:15", + "score": -0.09255108871392263, + "first_commit": "2023-01-18 11:14:31", + "latest_commit": "2023-01-21 02:10:41", "languages": [], "model_or_dataset": "model", - "model_size": 7.72, + "model_size": null, "model_architectures": null }, { - "description": "This model is a merged version of qwen-14b-vntl and Qwen1.5-14B-Chat , aiming for the translation of Japanese context into Chinese.", - "url": "https://huggingface.co/GralchemOz/Qwen1.5-14B-vntl-jp2zh-4.5bpw-h6-exl2", - "project_name": "Qwen1.5-14B-vntl-jp2zh-4.5bpw-h6-exl2", + "description": "Fine-tuned Japanese Whisper model for speech recognition using whisper-base Fine-tuned openai/whisper-base on Japanese using Common Voice, JVS and JSUT.", + "url": "https://huggingface.co/Ivydata/whisper-base-japanese", + "project_name": "whisper-base-japanese", "downloads": 23, "source": "Hugging Face", - "score": -0.11408453627123276, - "first_commit": "2024-03-03 02:29:43", - "latest_commit": "2024-03-03 03:17:09", + "score": -0.09255108871392263, + "first_commit": "2023-05-17 04:36:41", + "latest_commit": "2023-06-08 00:17:50", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "Qwen2ForCausalLM" + "model_architectures": "WhisperForConditionalGeneration" }, { - "description": "BERT for Japanese Twitter", - "url": "https://huggingface.co/LoneWolfgang/bert-for-japanese-twitter", - "project_name": "bert-for-japanese-twitter", + "description": "モデルの説明(English explanation is below.", + "url": "https://huggingface.co/keitokei1994/Llama-3-Umievo-Shizuko-sqlcoder-2x8B", + "project_name": "Llama-3-Umievo-Shizuko-sqlcoder-2x8B", "downloads": 23, "source": "Hugging Face", - "score": -0.11408453627123276, - "first_commit": "2024-05-06 15:53:21", - "latest_commit": "2024-08-09 12:24:35", + "score": -0.09255108871392263, + "first_commit": "2024-06-09 12:17:00", + "latest_commit": "2024-06-11 07:39:45", "languages": [], "model_or_dataset": "model", - "model_size": 0.111, - "model_architectures": "BertForMaskedLM" + "model_size": 13.7, + "model_architectures": "MixtralForCausalLM" }, { - "description": "JaWiki WikipediaのHTML形式のダンプファイルから抽出したテキストデータセットです。 ", - "url": "https://huggingface.co/datasets/hpprc/jawiki", - "project_name": "jawiki", + "description": "deberta-base-japanese-wikipedia-ud-goeswith Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-wikipedia-ud-goeswith", + "project_name": "deberta-base-japanese-wikipedia-ud-goeswith", "downloads": 23, "source": "Hugging Face", - "score": -0.11408453627123276, - "first_commit": "2024-02-02 06:36:01", - "latest_commit": "2024-02-13 15:19:49", + "score": -0.09255108871392263, + "first_commit": "2022-09-18 06:02:55", + "latest_commit": "2024-08-20 19:38:50", "languages": [], - "model_or_dataset": "dataset", + "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "JAINU-Model (T5 fine-tuned model) JAINU is a Japanese - Ainu language machine translation model. ", - "url": "https://huggingface.co/astremo/JAINU", - "project_name": "JAINU", - "downloads": 22, + "description": "deberta-large-japanese-aozora-ud-head Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-aozora-ud-head", + "project_name": "deberta-large-japanese-aozora-ud-head", + "downloads": 23, "source": "Hugging Face", - "score": -0.11410024762792698, - "first_commit": "2022-04-30 13:57:31", - "latest_commit": "2022-05-22 05:51:12", + "score": -0.09255108871392263, + "first_commit": "2022-06-17 15:00:25", + "latest_commit": "2023-03-04 20:17:12", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "T5ForConditionalGeneration" + "model_architectures": "DebertaV2ForQuestionAnswering" }, { - "description": "bart-base-japanese-news(base-sized model)", - "url": "https://huggingface.co/stockmark/bart-base-japanese-news", - "project_name": "bart-base-japanese-news", + "description": "名言推論モデル", + "url": "https://huggingface.co/Momerio/meigen_generate_Japanese", + "project_name": "meigen_generate_Japanese", "downloads": 22, "source": "Hugging Face", - "score": -0.11410024762792698, - "first_commit": "2023-01-20 04:23:07", - "latest_commit": "2023-12-08 03:39:50", + "score": -0.09256169366445897, + "first_commit": "2021-10-13 15:30:14", + "latest_commit": "2021-10-26 01:19:59", "languages": [], "model_or_dataset": "model", - "model_size": 0.125, - "model_architectures": "BartForConditionalGeneration" + "model_size": null, + "model_architectures": "GPT2LMHeadModel" }, { - "description": "bert-base-japanese-v3-bpr-passage-aio 「大規模言語モデル入門」の第9章で紹介している文書検索モデルBPRのパッセージエンコーダです。 ", - "url": "https://huggingface.co/llm-book/bert-base-japanese-v3-bpr-passage-aio", - "project_name": "bert-base-japanese-v3-bpr-passage-aio", + "description": "deberta-large-japanese-wikipedia Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-wikipedia", + "project_name": "deberta-large-japanese-wikipedia", "downloads": 22, "source": "Hugging Face", - "score": -0.11410024762792698, - "first_commit": "2023-06-06 08:22:28", - "latest_commit": "2023-07-24 07:14:59", + "score": -0.09256169366445897, + "first_commit": "2022-07-05 22:01:16", + "latest_commit": "2023-02-27 10:15:35", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "BertModel" + "model_architectures": "DebertaV2ForMaskedLM" }, { - "description": "Orion-14B 🌐English | 🇨", - "url": "https://huggingface.co/OrionStarAI/Orion-14B-Base-Int4", - "project_name": "Orion-14B-Base-Int4", + "description": "japanese-sexual-moderation-v2は、studio-ousia/luke-japanese-large-liteをファインチューニングしたモデルです。", + "url": "https://huggingface.co/oshizo/japanese-sexual-moderation-v2", + "project_name": "japanese-sexual-moderation-v2", "downloads": 22, "source": "Hugging Face", - "score": -0.11410024762792698, - "first_commit": "2024-01-18 09:50:31", - "latest_commit": "2024-03-26 09:55:37", + "score": -0.09256169366445897, + "first_commit": "2024-01-03 04:58:17", + "latest_commit": "2024-01-03 07:09:05", "languages": [], "model_or_dataset": "model", - "model_size": 2.69, - "model_architectures": "OrionForCausalLM" + "model_size": 0.41400000000000003, + "model_architectures": "LukeForSequenceClassification" }, { - "description": "Ninja-v1-RP-expressive GGUF版はこちら/Click here for the GGUF version 概要 This is a merge of pre-trained language models created using mergekit. ", - "url": "https://huggingface.co/Aratako/Ninja-v1-RP-expressive", - "project_name": "Ninja-v1-RP-expressive", + "description": "rinna/nekomata-14b-instruction-gguf Overview The model is the GGUF version of rinna/nekomata-14b-instruction.", + "url": "https://huggingface.co/rinna/nekomata-14b-instruction-gguf", + "project_name": "nekomata-14b-instruction-gguf", "downloads": 22, "source": "Hugging Face", - "score": -0.11410024762792698, - "first_commit": "2024-05-21 12:11:38", - "latest_commit": "2024-05-24 15:11:43", + "score": -0.09256169366445897, + "first_commit": "2023-12-19 08:12:06", + "latest_commit": "2024-07-20 08:34:05", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": "MistralForCausalLM" + "model_size": 14.2, + "model_architectures": null }, { "description": "llm-jp-13b-instruct-lora-jaster-v1.0", @@ -11113,7 +11494,7 @@ "project_name": "llm-jp-13b-instruct-lora-jaster-v1.0", "downloads": 22, "source": "Hugging Face", - "score": -0.11410024762792698, + "score": -0.09256169366445897, "first_commit": "2023-10-18 18:53:58", "latest_commit": "2023-10-20 08:41:20", "languages": [], @@ -11122,32 +11503,46 @@ "model_architectures": null }, { - "description": "deberta-base-japanese-upos Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-upos", - "project_name": "deberta-base-japanese-upos", + "description": "nlp-waseda/gpt2-xl-japanese This is Japanese GPT2 with approximately 1.5B parameters pretrained on Japanese Wikipedia and CC-100", + "url": "https://huggingface.co/nlp-waseda/gpt2-xl-japanese", + "project_name": "gpt2-xl-japanese", "downloads": 22, "source": "Hugging Face", - "score": -0.11410024762792698, - "first_commit": "2022-05-24 08:12:05", - "latest_commit": "2024-07-26 15:59:24", + "score": -0.09256169366445897, + "first_commit": "2022-11-30 04:33:31", + "latest_commit": "2023-06-21 04:29:10", + "languages": [], + "model_or_dataset": "model", + "model_size": 1.61, + "model_architectures": "GPT2LMHeadModel" + }, + { + "description": "bert-large-japanese-unidic-luw-upos Model Description", + "url": "https://huggingface.co/KoichiYasuoka/bert-large-japanese-unidic-luw-upos", + "project_name": "bert-large-japanese-unidic-luw-upos", + "downloads": 22, + "source": "Hugging Face", + "score": -0.09256169366445897, + "first_commit": "2022-02-13 01:00:41", + "latest_commit": "2023-11-05 18:44:20", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForTokenClassification" + "model_architectures": "BertForTokenClassification" }, { - "description": "This is a Japanese sentence-T5 model.", - "url": "https://huggingface.co/sonoisa/sentence-t5-base-ja-mean-tokens", - "project_name": "sentence-t5-base-ja-mean-tokens", + "description": "jpn-heb source group: Japanese target group:", + "url": "https://huggingface.co/Helsinki-NLP/opus-mt-ja-he", + "project_name": "opus-mt-ja-he", "downloads": 22, "source": "Hugging Face", - "score": -0.11410024762792698, - "first_commit": "2021-12-27 11:57:10", - "latest_commit": "2022-07-31 07:54:13", + "score": -0.09256169366445897, + "first_commit": "2020-08-19 00:28:58", + "latest_commit": "2023-08-16 11:59:12", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "T5Model" + "model_architectures": "MarianMTModel" }, { "description": "Heron GIT Japanese StableLM", @@ -11155,7 +11550,7 @@ "project_name": "heron-chat-git-ja-stablelm-base-7b-v1", "downloads": 22, "source": "Hugging Face", - "score": -0.11410024762792698, + "score": -0.09256169366445897, "first_commit": "2024-03-29 09:09:32", "latest_commit": "2024-05-02 07:55:57", "languages": [], @@ -11169,7 +11564,7 @@ "project_name": "CAMERA", "downloads": 22, "source": "Hugging Face", - "score": -0.11410024762792698, + "score": -0.09256169366445897, "first_commit": "2023-03-17 23:02:32", "latest_commit": "2023-03-17 23:49:35", "languages": [], @@ -11178,256 +11573,270 @@ "model_architectures": null }, { - "description": "This is for (private) DEMO only.", - "url": "https://huggingface.co/Bagus/wav2vec2-xlsr-japanese-speech-emotion-recognition", - "project_name": "wav2vec2-xlsr-japanese-speech-emotion-recognition", - "downloads": 21, + "description": "Dataset Description This is the Japanese Translation version of sciq.", + "url": "https://huggingface.co/datasets/izumi-lab/sciq-ja-mbartm2m", + "project_name": "sciq-ja-mbartm2m", + "downloads": 22, "source": "Hugging Face", - "score": -0.1141159589846212, - "first_commit": "2021-09-22 04:10:36", - "latest_commit": "2023-10-19 01:31:17", + "score": -0.09256169366445897, + "first_commit": "2023-05-19 02:03:47", + "latest_commit": "2023-05-19 03:54:18", "languages": [], - "model_or_dataset": "model", - "model_size": 0.316, - "model_architectures": "HubertForSequenceClassification" + "model_or_dataset": "dataset", + "model_size": null, + "model_architectures": null }, { - "description": "GPT2 Japanese base model version 2 Prerequisites transformers==4.19.2 Model architecture This model uses GPT2 base setttings except vocabulary size.", - "url": "https://huggingface.co/ClassCat/gpt2-base-japanese-v2", - "project_name": "gpt2-base-japanese-v2", + "description": "jpn-msa source group: Japanese target group: Malay (macrolanguage) OPUS readme: jpn-msa model: transformer-align source language(s): jpn jpn_Hani jpn_Hira jpn_Kana target language(s): ind", + "url": "https://huggingface.co/Helsinki-NLP/opus-mt-ja-ms", + "project_name": "opus-mt-ja-ms", "downloads": 21, "source": "Hugging Face", - "score": -0.1141159589846212, - "first_commit": "2022-06-04 02:30:34", - "latest_commit": "2022-06-25 15:36:22", + "score": -0.0925722986149953, + "first_commit": "2020-08-19 00:29:11", + "latest_commit": "2023-08-16 11:59:16", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "GPT2LMHeadModel" + "model_architectures": "MarianMTModel" }, { - "description": "alabnii/jmedroberta-base-sentencepiece-vocab50000 Model description This is a Japanese RoBERTa base model pre-trained on academic articles in medical sciences collected by Japan Science and Technology Agency (JST).", - "url": "https://huggingface.co/alabnii/jmedroberta-base-sentencepiece-vocab50000", - "project_name": "jmedroberta-base-sentencepiece-vocab50000", + "description": "BERT small Japanese finance This is a BERT model pretrained on texts in the Japanese language.", + "url": "https://huggingface.co/izumi-lab/bert-small-japanese-fin", + "project_name": "bert-small-japanese-fin", "downloads": 21, "source": "Hugging Face", - "score": -0.1141159589846212, - "first_commit": "2022-12-22 17:22:14", - "latest_commit": "2023-06-27 03:44:17", + "score": -0.0925722986149953, + "first_commit": "2021-10-04 13:15:37", + "latest_commit": "2022-12-09 00:41:24", "languages": [], "model_or_dataset": "model", - "model_size": 0.124, + "model_size": null, "model_architectures": "BertForMaskedLM" }, { - "description": "rinna/nekomata-14b-instruction-gguf Overview The model is the GGUF version of rinna/nekomata-14b-instruction.", - "url": "https://huggingface.co/rinna/nekomata-14b-instruction-gguf", - "project_name": "nekomata-14b-instruction-gguf", + "description": "deberta-base-japanese-upos Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-upos", + "project_name": "deberta-base-japanese-upos", "downloads": 21, "source": "Hugging Face", - "score": -0.1141159589846212, - "first_commit": "2023-12-19 08:12:06", - "latest_commit": "2024-07-20 08:34:05", + "score": -0.0925722986149953, + "first_commit": "2022-05-24 08:12:05", + "latest_commit": "2024-07-26 15:59:24", "languages": [], "model_or_dataset": "model", - "model_size": 14.2, - "model_architectures": null + "model_size": null, + "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "japanese-sexual-moderation-v2は、studio-ousia/luke-japanese-large-liteをファインチューニングしたモデルです。", - "url": "https://huggingface.co/oshizo/japanese-sexual-moderation-v2", - "project_name": "japanese-sexual-moderation-v2", + "description": "roberta-large-japanese-juman-ud-goeswith Model Description", + "url": "https://huggingface.co/KoichiYasuoka/roberta-large-japanese-juman-ud-goeswith", + "project_name": "roberta-large-japanese-juman-ud-goeswith", "downloads": 21, "source": "Hugging Face", - "score": -0.1141159589846212, - "first_commit": "2024-01-03 04:58:17", - "latest_commit": "2024-01-03 07:09:05", + "score": -0.0925722986149953, + "first_commit": "2023-02-21 06:38:32", + "latest_commit": "2024-08-30 14:49:26", "languages": [], "model_or_dataset": "model", - "model_size": 0.41400000000000003, - "model_architectures": "LukeForSequenceClassification" + "model_size": null, + "model_architectures": "RobertaForTokenClassification" }, { - "description": "Tanuki-8B-dpo-v1.0-AWQ 概要 GENIAC 松尾研 LLM開発プロジェクトで開発されたLLMであるweblab-GENIAC/Tanuki-8B-dpo-v1.0のAWQ 4bit量子化モデルです。", - "url": "https://huggingface.co/team-hatakeyama-phase2/Tanuki-8B-dpo-v1.0-AWQ", - "project_name": "Tanuki-8B-dpo-v1.0-AWQ", + "description": "Ruri-Reranker: Japanese General Reranker Usage Direct Usage (Sentence Transformers)", + "url": "https://huggingface.co/cl-nagoya/ruri-reranker-stage1-base", + "project_name": "ruri-reranker-stage1-base", "downloads": 21, "source": "Hugging Face", - "score": -0.1141159589846212, - "first_commit": "2024-08-27 04:50:35", - "latest_commit": "2024-09-03 09:29:23", + "score": -0.0925722986149953, + "first_commit": "2024-08-19 16:14:12", + "latest_commit": "2024-09-04 08:52:18", "languages": [], "model_or_dataset": "model", - "model_size": 1.47, - "model_architectures": "LlamaForCausalLM" + "model_size": 0.111, + "model_architectures": "BertForSequenceClassification" }, { - "description": "SambaLingo-Japanese-Chat SambaLingo-Japanese-Chat is a human aligned chat model trained in Japanese and English.", - "url": "https://huggingface.co/sambanovasystems/SambaLingo-Japanese-Chat", - "project_name": "SambaLingo-Japanese-Chat", + "description": "記事本文からタイトルを生成するモデル SEE: https://qiita.com/sonoisa/items/30876467ad5a8a81821f", + "url": "https://huggingface.co/sonoisa/t5-qiita-title-generation", + "project_name": "t5-qiita-title-generation", "downloads": 21, "source": "Hugging Face", - "score": -0.1141159589846212, - "first_commit": "2024-02-15 22:45:08", - "latest_commit": "2024-04-16 22:32:15", + "score": -0.0925722986149953, + "first_commit": "2021-10-17 14:46:56", + "latest_commit": "2022-02-21 13:39:01", "languages": [], "model_or_dataset": "model", - "model_size": 6.95, - "model_architectures": "LlamaForCausalLM" + "model_size": null, + "model_architectures": "T5ForConditionalGeneration" }, { - "description": "About This model is Lightblue's QLoRA finetune of OpenOrca's Open-Orca/OpenOrcaxOpenChat-Preview2-13B model on Japanese fine-tuning datasets.", - "url": "https://huggingface.co/lightblue/openorca_stx", - "project_name": "openorca_stx", + "description": "roberta-large-japanese-char-luw-upos Model Description", + "url": "https://huggingface.co/KoichiYasuoka/roberta-large-japanese-char-luw-upos", + "project_name": "roberta-large-japanese-char-luw-upos", "downloads": 21, "source": "Hugging Face", - "score": -0.1141159589846212, - "first_commit": "2023-09-12 09:29:10", - "latest_commit": "2023-10-02 10:25:36", + "score": -0.0925722986149953, + "first_commit": "2021-12-30 15:56:46", + "latest_commit": "2022-09-18 19:44:49", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "LlamaForCausalLM" + "model_architectures": "RobertaForTokenClassification" }, { - "description": "Japanese DialoGPT trained with Aozora (ja) 青空文庫のセリフで学習した日本語のDialoGPT Smallです(en) Japanese DialoGPT Small trained on Aozora Bunko.", - "url": "https://huggingface.co/akiFQC/japanese-dialogpt-small-aozora", - "project_name": "japanese-dialogpt-small-aozora", + "description": "Japanese-Heron-Bench Dataset Description Japanese-Heron-Bench is a benchmark for evaluating Japanese VLMs (Vision-Language Models).", + "url": "https://huggingface.co/datasets/turing-motors/Japanese-Heron-Bench", + "project_name": "Japanese-Heron-Bench", "downloads": 21, "source": "Hugging Face", - "score": -0.1141159589846212, - "first_commit": "2023-02-08 13:22:24", - "latest_commit": "2023-02-09 00:55:31", + "score": -0.0925722986149953, + "first_commit": "2024-04-12 01:54:01", + "latest_commit": "2024-04-12 08:59:36", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "GPT2LMHeadModel" + "model_architectures": null }, { - "description": "deberta-base-japanese-wikipedia-ud-head Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-wikipedia-ud-head", - "project_name": "deberta-base-japanese-wikipedia-ud-head", - "downloads": 21, + "description": "ELECTRA base Japanese generator This is a ELECTRA model pretrained on texts in the Japanese language.", + "url": "https://huggingface.co/izumi-lab/electra-base-japanese-generator", + "project_name": "electra-base-japanese-generator", + "downloads": 20, + "source": "Hugging Face", + "score": -0.09258290356553164, + "first_commit": "2021-11-15 17:23:50", + "latest_commit": "2023-10-21 13:21:16", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.035500000000000004, + "model_architectures": "ElectraForMaskedLM" + }, + { + "description": "yuyuyui-chatbot", + "url": "https://huggingface.co/ushikado/yuyuyui-chatbot", + "project_name": "yuyuyui-chatbot", + "downloads": 20, "source": "Hugging Face", - "score": -0.1141159589846212, - "first_commit": "2022-06-25 13:03:09", - "latest_commit": "2024-08-20 19:47:27", + "score": -0.09258290356553164, + "first_commit": "2021-05-04 14:52:12", + "latest_commit": "2021-05-23 13:27:10", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForQuestionAnswering" + "model_architectures": "GPT2LMHeadModel" }, { - "description": "jpn-msa source group: Japanese target group: Malay (macrolanguage) OPUS readme: jpn-msa model: transformer-align source language(s): jpn jpn_Hani jpn_Hira jpn_Kana target language(s): ind", - "url": "https://huggingface.co/Helsinki-NLP/opus-mt-ja-ms", - "project_name": "opus-mt-ja-ms", - "downloads": 21, + "description": "Japanese GPT2 Lyric Model Model description", + "url": "https://huggingface.co/skytnt/gpt2-japanese-lyric-medium", + "project_name": "gpt2-japanese-lyric-medium", + "downloads": 20, "source": "Hugging Face", - "score": -0.1141159589846212, - "first_commit": "2020-08-19 00:29:11", - "latest_commit": "2023-08-16 11:59:16", + "score": -0.09258290356553164, + "first_commit": "2022-07-08 13:28:12", + "latest_commit": "2023-10-21 14:53:57", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "MarianMTModel" + "model_size": 0.361, + "model_architectures": "GPT2LMHeadModel" }, { - "description": "J-ResearchCorpus Update: 2024/3/16言語処理学会第30回年次大会(NLP2024)を含む、論文 1,343 本のデータを追加 2024/2/25言語処理学会誌「自然言語処理」のうち CC-BY-4.0 で公開されている論文 360 本のデータを追加 概要 CC-BY-* ライセンスで公開されている日本語論文や学会誌等から抜粋した高品質なテキストのデータセットです。", - "url": "https://huggingface.co/datasets/kunishou/J-ResearchCorpus", - "project_name": "J-ResearchCorpus", - "downloads": 21, + "description": "deberta-large-japanese-juman-ud-goeswith Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-juman-ud-goeswith", + "project_name": "deberta-large-japanese-juman-ud-goeswith", + "downloads": 20, "source": "Hugging Face", - "score": -0.1141159589846212, - "first_commit": "2024-02-12 14:03:42", - "latest_commit": "2024-03-16 07:55:08", + "score": -0.09258290356553164, + "first_commit": "2023-02-05 13:24:47", + "latest_commit": "2024-08-30 14:27:11", "languages": [], - "model_or_dataset": "dataset", + "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "日本語でtrainingしたllama2 model size: 417.12M trainingは以下のscript参照https://github.com/Lightning-AI/lit-gpt/tree/main use from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained(\"if001/sentencepiece_ja\", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained(\"if001/llama2_ja_small\")", - "url": "https://huggingface.co/if001/llama2_ja_small", - "project_name": "llama2_ja_small", + "description": "bert-base-japanese-v3-bpr-passage-aio 「大規模言語モデル入門」の第9章で紹介している文書検索モデルBPRのパッセージエンコーダです。 ", + "url": "https://huggingface.co/llm-book/bert-base-japanese-v3-bpr-passage-aio", + "project_name": "bert-base-japanese-v3-bpr-passage-aio", "downloads": 20, "source": "Hugging Face", - "score": -0.11413167034131541, - "first_commit": "2023-10-11 09:11:41", - "latest_commit": "2023-10-14 13:50:54", + "score": -0.09258290356553164, + "first_commit": "2023-06-06 08:22:28", + "latest_commit": "2023-07-24 07:14:59", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "LlamaForCausalLM" + "model_architectures": "BertModel" }, { - "description": "deberta-base-japanese-aozora-ud-goeswith Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-aozora-ud-goeswith", - "project_name": "deberta-base-japanese-aozora-ud-goeswith", + "description": "transformer-lm-japanese-1.0b This is a JAX/Flax-based transformer language model trained on a Japanese dataset.", + "url": "https://huggingface.co/fukugawa/transformer-lm-japanese-1.0b", + "project_name": "transformer-lm-japanese-1.0b", "downloads": 20, "source": "Hugging Face", - "score": -0.11413167034131541, - "first_commit": "2022-10-14 09:43:58", - "latest_commit": "2024-08-20 18:52:19", + "score": -0.09258290356553164, + "first_commit": "2024-07-25 04:27:53", + "latest_commit": "2024-09-06 12:44:00", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForTokenClassification" + "model_architectures": "TransformerLMForCausalLM" }, { - "description": "deberta-large-japanese-upos Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-upos", - "project_name": "deberta-large-japanese-upos", + "description": "Style-Bert-VITS2 Japanese Only Sakura Miko こちらは「さくらみこ」の音声データセットに基づいて学習されたVITS-TTSモデルです。 ", + "url": "https://huggingface.co/Lycoris53/style-bert-vits2-sakura-miko", + "project_name": "style-bert-vits2-sakura-miko", "downloads": 20, "source": "Hugging Face", - "score": -0.11413167034131541, - "first_commit": "2022-05-27 06:50:55", - "latest_commit": "2024-07-26 16:00:59", + "score": -0.09258290356553164, + "first_commit": "2024-05-27 14:58:38", + "latest_commit": "2024-05-28 03:02:14", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForTokenClassification" + "model_architectures": null }, { - "description": "deberta-base-japanese-aozora Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-aozora", - "project_name": "deberta-base-japanese-aozora", + "description": "Model card for model ID", + "url": "https://huggingface.co/retrieva-jp/t5-base-short", + "project_name": "t5-base-short", "downloads": 20, "source": "Hugging Face", - "score": -0.11413167034131541, - "first_commit": "2022-05-24 04:30:28", - "latest_commit": "2023-01-08 08:41:04", + "score": -0.09258290356553164, + "first_commit": "2023-04-26 08:20:52", + "latest_commit": "2023-05-10 10:00:23", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForMaskedLM" + "model_architectures": "T5ForConditionalGeneration" }, { - "description": "deberta-small-japanese-aozora Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-small-japanese-aozora", - "project_name": "deberta-small-japanese-aozora", + "description": "JAINU-Model (T5 fine-tuned model) JAINU is a Japanese - Ainu language machine translation model. ", + "url": "https://huggingface.co/astremo/JAINU", + "project_name": "JAINU", "downloads": 20, "source": "Hugging Face", - "score": -0.11413167034131541, - "first_commit": "2022-05-23 04:58:53", - "latest_commit": "2023-01-15 15:25:14", + "score": -0.09258290356553164, + "first_commit": "2022-04-30 13:57:31", + "latest_commit": "2022-05-22 05:51:12", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForMaskedLM" + "model_architectures": "T5ForConditionalGeneration" }, { - "description": "Genji-JP 6B Please check our blog post for more details, samples, evaluations and more: Blogpost Model Description Genji-JP 6B is a model finetuned on our Japanese storytelling dataset based on EleutherAI's GPT-J 6B model.", - "url": "https://huggingface.co/NovelAI/genji-jp", - "project_name": "genji-jp", + "description": "TinySlime-1.1B-Chat-v1.0 TinySlime は日本語に特化した小規模言語モデルです。 ", + "url": "https://huggingface.co/2121-8/TinySlime-1.1B-Chat-v1.0", + "project_name": "TinySlime-1.1B-Chat-v1.0", "downloads": 20, "source": "Hugging Face", - "score": -0.11413167034131541, - "first_commit": "2021-11-03 15:07:47", - "latest_commit": "2022-08-09 17:36:02", + "score": -0.09258290356553164, + "first_commit": "2024-07-02 03:34:30", + "latest_commit": "2024-07-02 08:53:11", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "GPTJForCausalLM" + "model_size": 1.1, + "model_architectures": "LlamaForCausalLM" }, { "description": ", 2023) was trained on.", @@ -11435,7 +11844,7 @@ "project_name": "lima-ja", "downloads": 20, "source": "Hugging Face", - "score": -0.11413167034131541, + "score": -0.09258290356553164, "first_commit": "2023-07-08 07:35:34", "latest_commit": "2023-07-08 13:39:45", "languages": [], @@ -11449,7 +11858,7 @@ "project_name": "JParaCrawl", "downloads": 20, "source": "Hugging Face", - "score": -0.11413167034131541, + "score": -0.09258290356553164, "first_commit": "2024-08-24 15:07:12", "latest_commit": "2024-08-25 13:15:52", "languages": [], @@ -11458,74 +11867,74 @@ "model_architectures": null }, { - "description": "Convert from: drewschaub/whisper-large-v3-japanese-4k-steps Whisper large-v3 model for CTranslate2 This repository contains the conversion of drewschaub/whisper-large-v3-japanese-4k-steps to the CTranslate2 model format.", - "url": "https://huggingface.co/JhonVanced/whisper-large-v3-japanese-4k-steps-ct2", - "project_name": "whisper-large-v3-japanese-4k-steps-ct2", - "downloads": 19, + "description": "Dataset Summary JMultiWOZ is a large-scale Japanese multi-domain task-oriented dialogue dataset.", + "url": "https://huggingface.co/datasets/nu-dialogue/jmultiwoz", + "project_name": "jmultiwoz", + "downloads": 20, "source": "Hugging Face", - "score": -0.11414738169800963, - "first_commit": "2024-02-20 13:41:17", - "latest_commit": "2024-02-22 01:11:59", + "score": -0.09258290356553164, + "first_commit": "2024-02-29 15:38:29", + "latest_commit": "2024-03-13 02:15:37", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "yuyuyui-chatbot", - "url": "https://huggingface.co/ushikado/yuyuyui-chatbot", - "project_name": "yuyuyui-chatbot", + "description": "gpt2-small-japanese-ud-causal Model Description", + "url": "https://huggingface.co/KoichiYasuoka/gpt2-small-japanese-ud-causal", + "project_name": "gpt2-small-japanese-ud-causal", "downloads": 19, "source": "Hugging Face", - "score": -0.11414738169800963, - "first_commit": "2021-05-04 14:52:12", - "latest_commit": "2021-05-23 13:27:10", + "score": -0.09259350851606797, + "first_commit": "2024-08-22 13:33:02", + "latest_commit": "2024-08-25 17:54:09", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "GPT2LMHeadModel" + "model_architectures": "GPT2ForTokenClassification" }, { - "description": "deberta-large-japanese-aozora-ud-goeswith Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-aozora-ud-goeswith", - "project_name": "deberta-large-japanese-aozora-ud-goeswith", + "description": "Genji-JP 6B Please check our blog post for more details, samples, evaluations and more: Blogpost Model Description Genji-JP 6B is a model finetuned on our Japanese storytelling dataset based on EleutherAI's GPT-J 6B model.", + "url": "https://huggingface.co/NovelAI/genji-jp", + "project_name": "genji-jp", "downloads": 19, "source": "Hugging Face", - "score": -0.11414738169800963, - "first_commit": "2022-10-14 11:35:36", - "latest_commit": "2024-08-20 19:20:44", + "score": -0.09259350851606797, + "first_commit": "2021-11-03 15:07:47", + "latest_commit": "2022-08-09 17:36:02", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForTokenClassification" + "model_architectures": "GPTJForCausalLM" }, { - "description": "Heron BLIP Japanese StableLM", - "url": "https://huggingface.co/turing-motors/heron-chat-blip-ja-stablelm-base-7b-v0", - "project_name": "heron-chat-blip-ja-stablelm-base-7b-v0", + "description": "spekulatius マージしているとたまに出てくる「目的の意図とは違うのだけどなんだか消すにはもったいないモデル」をおすそ分けするシリーズです。 ", + "url": "https://huggingface.co/Lasorco/spekulatius", + "project_name": "spekulatius", "downloads": 19, "source": "Hugging Face", - "score": -0.11414738169800963, - "first_commit": "2023-09-06 09:31:44", - "latest_commit": "2023-09-07 16:59:14", + "score": -0.09259350851606797, + "first_commit": "2023-10-24 13:56:21", + "latest_commit": "2023-10-26 04:21:35", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "VideoBlipForConditionalGeneration" + "model_architectures": null }, { - "description": "Chat & support: TheBloke's Discord server Want to contribute?", - "url": "https://huggingface.co/TheBloke/japanese-stablelm-instruct-beta-70B-AWQ", - "project_name": "japanese-stablelm-instruct-beta-70B-AWQ", + "description": "XML-RoBERTa-NER-Japanese This model is a fine-tuned version of xlm-roberta-base on the Wikipedia Japanese NER dataset from Stockmark Inc.", + "url": "https://huggingface.co/ithattieu/XML-RoBERTa-NER-Japanese", + "project_name": "XML-RoBERTa-NER-Japanese", "downloads": 19, "source": "Hugging Face", - "score": -0.11414738169800963, - "first_commit": "2023-11-02 15:45:23", - "latest_commit": "2023-11-09 18:16:16", + "score": -0.09259350851606797, + "first_commit": "2024-08-17 08:18:04", + "latest_commit": "2024-08-18 04:03:33", "languages": [], "model_or_dataset": "model", - "model_size": 9.68, - "model_architectures": "LlamaForCausalLM" + "model_size": 0.277, + "model_architectures": "RobertaForTokenClassification" }, { "description": "BERT for Sentiment Analysis of Japanese Twitter", @@ -11533,7 +11942,7 @@ "project_name": "bert-for-japanese-twitter-sentiment-mixed-label", "downloads": 19, "source": "Hugging Face", - "score": -0.11414738169800963, + "score": -0.09259350851606797, "first_commit": "2024-08-09 11:38:05", "latest_commit": "2024-08-09 12:10:35", "languages": [], @@ -11542,116 +11951,88 @@ "model_architectures": "BertForSequenceClassification" }, { - "description": "Style-Bert-VITS2 Japanese Only Sakura Miko こちらは「さくらみこ」の音声データセットに基づいて学習されたVITS-TTSモデルです。 ", - "url": "https://huggingface.co/Lycoris53/style-bert-vits2-sakura-miko", - "project_name": "style-bert-vits2-sakura-miko", - "downloads": 19, - "source": "Hugging Face", - "score": -0.11414738169800963, - "first_commit": "2024-05-27 14:58:38", - "latest_commit": "2024-05-28 03:02:14", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": null - }, - { - "description": "karasu-lora-jp-qa-chat karasu fine tuned model by lora method with the original Q&A dataset.", - "url": "https://huggingface.co/aipib/karasu-lora-jp-qa-chat", - "project_name": "karasu-lora-jp-qa-chat", - "downloads": 19, - "source": "Hugging Face", - "score": -0.11414738169800963, - "first_commit": "2024-04-24 02:26:58", - "latest_commit": "2024-06-03 01:02:33", - "languages": [], - "model_or_dataset": "model", - "model_size": 1.1, - "model_architectures": "LlamaForCausalLM" - }, - { - "description": "Chat & support: TheBloke's Discord server Want to contribute?", - "url": "https://huggingface.co/TheBloke/japanese-stablelm-base-beta-70B-AWQ", - "project_name": "japanese-stablelm-base-beta-70B-AWQ", + "description": "275.86Mのmixtralを日本語データセットでpretrainingしたものです sample from transformers import AutoTokenizer, AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained(\"if001/tiny_mixtral_ja\")", + "url": "https://huggingface.co/hibikaze/tiny_mixtral_ja_with_tokenizer", + "project_name": "tiny_mixtral_ja_with_tokenizer", "downloads": 19, "source": "Hugging Face", - "score": -0.11414738169800963, - "first_commit": "2023-11-06 11:33:47", - "latest_commit": "2023-11-09 18:16:05", + "score": -0.09259350851606797, + "first_commit": "2024-07-20 05:30:59", + "latest_commit": "2024-07-20 05:33:38", "languages": [], "model_or_dataset": "model", - "model_size": 9.68, - "model_architectures": "LlamaForCausalLM" + "model_size": 0.276, + "model_architectures": "MixtralForCausalLM" }, { - "description": "こちらでアップロードできないので、civitaiにて先に公開しています。 ", - "url": "https://huggingface.co/sazyou-roukaku/AfterRealXL", - "project_name": "AfterRealXL", + "description": "Model Card for Japanese character-level GPT-2 Large Model description", + "url": "https://huggingface.co/ku-nlp/gpt2-large-japanese-char", + "project_name": "gpt2-large-japanese-char", "downloads": 19, "source": "Hugging Face", - "score": -0.11414738169800963, - "first_commit": "2023-09-23 08:43:02", - "latest_commit": "2023-10-01 18:12:09", + "score": -0.09259350851606797, + "first_commit": "2023-12-27 11:18:45", + "latest_commit": "2023-12-27 12:07:30", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "GPT2LMHeadModel" }, { - "description": "deberta-large-japanese-wikipedia-ud-head Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-wikipedia-ud-head", - "project_name": "deberta-large-japanese-wikipedia-ud-head", + "description": "Wav2Vec2-XLS-R-300M-Japanese-Hiragana Fine-tuned facebook/wav2vec2-xls-r-300m on Japanese Hiragana characters using the Common Voice and JSUT.", + "url": "https://huggingface.co/slplab/wav2vec2-xls-r-300m-japanese-hiragana", + "project_name": "wav2vec2-xls-r-300m-japanese-hiragana", "downloads": 19, "source": "Hugging Face", - "score": -0.11414738169800963, - "first_commit": "2022-07-06 03:51:14", - "latest_commit": "2024-08-20 19:51:21", + "score": -0.09259350851606797, + "first_commit": "2022-09-16 07:34:58", + "latest_commit": "2022-09-16 11:01:54", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForQuestionAnswering" + "model_architectures": "Wav2Vec2ForCTC" }, { - "description": "nlp-waseda/gpt2-small-japanese This model is Japanese GPT-2 pretrained on Japanese Wikipedia and CC-100.", - "url": "https://huggingface.co/nlp-waseda/gpt2-small-japanese", - "project_name": "gpt2-small-japanese", + "description": "deberta-small-japanese-aozora Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-small-japanese-aozora", + "project_name": "deberta-small-japanese-aozora", "downloads": 19, "source": "Hugging Face", - "score": -0.11414738169800963, - "first_commit": "2022-03-30 03:34:11", - "latest_commit": "2022-03-30 04:28:17", + "score": -0.09259350851606797, + "first_commit": "2022-05-23 04:58:53", + "latest_commit": "2023-01-15 15:25:14", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "GPT2LMHeadModel" + "model_architectures": "DebertaV2ForMaskedLM" }, { - "description": "日本語T5事前学習済みモデル This is a T5 (Text-to-Text Transfer Transformer) model pretrained on Japanese corpus. ", - "url": "https://huggingface.co/sonoisa/t5-base-japanese-mC4-Wikipedia", - "project_name": "t5-base-japanese-mC4-Wikipedia", + "description": "Model Overview: 日本語で質問すると、日本語で回答を得られます。", + "url": "https://huggingface.co/Ryu-m0m/16bit-japanese-finetuned-mistral-7b-v0", + "project_name": "16bit-japanese-finetuned-mistral-7b-v0", "downloads": 19, "source": "Hugging Face", - "score": -0.11414738169800963, - "first_commit": "2021-06-30 12:53:09", - "latest_commit": "2021-09-23 18:29:58", + "score": -0.09259350851606797, + "first_commit": "2024-08-20 14:33:15", + "latest_commit": "2024-08-21 15:31:43", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "MistralForCausalLM" }, { - "description": "Model Overview: 日本語で質問すると、日本語で回答を得られます。", - "url": "https://huggingface.co/Ryu-m0m/16bit-japanese-finetuned-mistral-7b-v0", - "project_name": "16bit-japanese-finetuned-mistral-7b-v0", + "description": "Japanese-Law-Translation Dataset Summary", + "url": "https://huggingface.co/datasets/Hoshikuzu/Japanese-Law-Translation", + "project_name": "Japanese-Law-Translation", "downloads": 19, "source": "Hugging Face", - "score": -0.11414738169800963, - "first_commit": "2024-08-20 14:33:15", - "latest_commit": "2024-08-21 15:31:43", + "score": -0.09259350851606797, + "first_commit": "2024-08-24 14:43:16", + "latest_commit": "2024-08-25 13:26:11", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "MistralForCausalLM" + "model_architectures": null }, { "description": "mqaデータセットのquery--passageのペアについて重複を削除したデータセットです。 ", @@ -11659,7 +12040,7 @@ "project_name": "mqa-ja", "downloads": 19, "source": "Hugging Face", - "score": -0.11414738169800963, + "score": -0.09259350851606797, "first_commit": "2024-04-07 06:23:02", "latest_commit": "2024-04-07 15:16:42", "languages": [], @@ -11668,74 +12049,74 @@ "model_architectures": null }, { - "description": "Japanese-Law-Translation Dataset Summary", - "url": "https://huggingface.co/datasets/Hoshikuzu/Japanese-Law-Translation", - "project_name": "Japanese-Law-Translation", + "description": "For more information, see website below!", + "url": "https://huggingface.co/datasets/Hoshikuzu/Tanaka-corpus", + "project_name": "Tanaka-corpus", "downloads": 19, "source": "Hugging Face", - "score": -0.11414738169800963, - "first_commit": "2024-08-24 14:43:16", - "latest_commit": "2024-08-25 13:26:11", + "score": -0.09259350851606797, + "first_commit": "2024-08-24 14:51:15", + "latest_commit": "2024-08-25 13:20:34", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "For more information, see website below!", - "url": "https://huggingface.co/datasets/Hoshikuzu/Tanaka-corpus", - "project_name": "Tanaka-corpus", + "description": "It covers multiple fields such as tourism, medical treatment, daily life, news, etc. ", + "url": "https://huggingface.co/datasets/Nexdata/English-Japanese_Parallel_Corpus_Data", + "project_name": "English-Japanese_Parallel_Corpus_Data", "downloads": 19, "source": "Hugging Face", - "score": -0.11414738169800963, - "first_commit": "2024-08-24 14:51:15", - "latest_commit": "2024-08-25 13:20:34", + "score": -0.09259350851606797, + "first_commit": "2023-11-08 10:47:40", + "latest_commit": "2024-08-05 03:14:27", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "Mixtral-8x7B-Instruct-v0.1-japanese Mixtral-8x7B-Instruct-v0.1-japaneseはMixtral-8x7B-Instruct-v0.1をベースに日本語の語彙拡張継続事前学習を実施したモデルです。", - "url": "https://huggingface.co/abeja/Mixtral-8x7B-Instruct-v0.1-japanese", - "project_name": "Mixtral-8x7B-Instruct-v0.1-japanese", + "description": "bert-base-japanese-char-extended Model Description", + "url": "https://huggingface.co/KoichiYasuoka/bert-base-japanese-char-extended", + "project_name": "bert-base-japanese-char-extended", "downloads": 18, "source": "Hugging Face", - "score": -0.11416309305470385, - "first_commit": "2024-04-17 02:56:15", - "latest_commit": "2024-04-20 09:14:27", + "score": -0.09260411346660431, + "first_commit": "2021-08-26 22:44:12", + "latest_commit": "2022-06-21 07:21:54", "languages": [], "model_or_dataset": "model", - "model_size": 46.9, - "model_architectures": "MixtralForCausalLM" + "model_size": null, + "model_architectures": "BertForMaskedLM" }, { - "description": "gpt2-small-japanese-upos Model Description", - "url": "https://huggingface.co/KoichiYasuoka/gpt2-small-japanese-upos", - "project_name": "gpt2-small-japanese-upos", + "description": "deberta-large-japanese-unidic-luw-upos Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-unidic-luw-upos", + "project_name": "deberta-large-japanese-unidic-luw-upos", "downloads": 18, "source": "Hugging Face", - "score": -0.11416309305470385, - "first_commit": "2024-06-22 22:28:58", - "latest_commit": "2024-07-27 07:49:34", + "score": -0.09260411346660431, + "first_commit": "2022-06-10 12:53:45", + "latest_commit": "2024-08-20 20:16:18", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "GPT2ForTokenClassification" + "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "SpiralAI Spiral-RetNet-3b-base We have conducted pre-training from scratch on the RetNet (https://arxiv.org/abs/2307.08621)", - "url": "https://huggingface.co/Spiral-AI/Spiral-RetNet-3b-base", - "project_name": "Spiral-RetNet-3b-base", + "description": "GPT2 Japanese base model version 2 Prerequisites transformers==4.19.2 Model architecture This model uses GPT2 base setttings except vocabulary size.", + "url": "https://huggingface.co/ClassCat/gpt2-base-japanese-v2", + "project_name": "gpt2-base-japanese-v2", "downloads": 18, "source": "Hugging Face", - "score": -0.11416309305470385, - "first_commit": "2024-04-30 09:33:26", - "latest_commit": "2024-05-01 04:54:26", + "score": -0.09260411346660431, + "first_commit": "2022-06-04 02:30:34", + "latest_commit": "2022-06-25 15:36:22", "languages": [], "model_or_dataset": "model", - "model_size": 2.86, - "model_architectures": "RetNetForCausalLM" + "model_size": null, + "model_architectures": "GPT2LMHeadModel" }, { "description": "Donut (base-sized model, fine-tuned on visual novel like synthetic dataset ) ビジュアルノベル風画像の合成データセットでnaver-clova-ix/donut-baseを訓練したモデルです。 ", @@ -11743,7 +12124,7 @@ "project_name": "donut-base-japanese-visual-novel", "downloads": 18, "source": "Hugging Face", - "score": -0.11416309305470385, + "score": -0.09260411346660431, "first_commit": "2023-05-03 04:53:49", "latest_commit": "2023-05-03 09:25:19", "languages": [], @@ -11752,28 +12133,112 @@ "model_architectures": "VisionEncoderDecoderModel" }, { - "description": "Japanese Stable Diffusion Pokemon Model Card Stable-Diffusion-Pokemon-ja is a Japanese-specific latent text-to-image diffusion model capable of generating Pokemon images given any text input.", - "url": "https://huggingface.co/svjack/Stable-Diffusion-Pokemon-ja", - "project_name": "Stable-Diffusion-Pokemon-ja", + "description": "karasu-lora-jp-qa-chat karasu fine tuned model by lora method with the original Q&A dataset.", + "url": "https://huggingface.co/aipib/karasu-lora-jp-qa-chat", + "project_name": "karasu-lora-jp-qa-chat", "downloads": 18, "source": "Hugging Face", - "score": -0.11416309305470385, - "first_commit": "2022-10-30 08:19:13", - "latest_commit": "2023-05-16 09:23:49", + "score": -0.09260411346660431, + "first_commit": "2024-04-24 02:26:58", + "latest_commit": "2024-06-03 01:02:33", + "languages": [], + "model_or_dataset": "model", + "model_size": 1.1, + "model_architectures": "LlamaForCausalLM" + }, + { + "description": "Tanuki-8B-dpo-v1.0-GPTQ-8bit 概要 GENIAC 松尾研 LLM開発プロジェクトで開発されたLLMであるweblab-GENIAC/Tanuki-8B-dpo-v1.0のGPTQ 8bit量子化モデルです。", + "url": "https://huggingface.co/team-hatakeyama-phase2/Tanuki-8B-dpo-v1.0-GPTQ-8bit", + "project_name": "Tanuki-8B-dpo-v1.0-GPTQ-8bit", + "downloads": 18, + "source": "Hugging Face", + "score": -0.09260411346660431, + "first_commit": "2024-08-27 17:32:47", + "latest_commit": "2024-09-03 09:28:59", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "LlamaForCausalLM" }, { - "description": "Japanese-Heron-Bench Dataset Description Japanese-Heron-Bench is a benchmark for evaluating Japanese VLMs (Vision-Language Models).", - "url": "https://huggingface.co/datasets/turing-motors/Japanese-Heron-Bench", - "project_name": "Japanese-Heron-Bench", + "description": "This model is a merged version of qwen-14b-vntl and Qwen1.5-14B-Chat , aiming for the translation of Japanese context into Chinese.", + "url": "https://huggingface.co/GralchemOz/Qwen1.5-14B-vntl-jp2zh-4.5bpw-h6-exl2", + "project_name": "Qwen1.5-14B-vntl-jp2zh-4.5bpw-h6-exl2", "downloads": 18, "source": "Hugging Face", - "score": -0.11416309305470385, - "first_commit": "2024-04-12 01:54:01", - "latest_commit": "2024-04-12 08:59:36", + "score": -0.09260411346660431, + "first_commit": "2024-03-03 02:29:43", + "latest_commit": "2024-03-03 03:17:09", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "Qwen2ForCausalLM" + }, + { + "description": "Chat & support: TheBloke's Discord server Want to contribute?", + "url": "https://huggingface.co/TheBloke/japanese-stablelm-base-beta-70B-AWQ", + "project_name": "japanese-stablelm-base-beta-70B-AWQ", + "downloads": 18, + "source": "Hugging Face", + "score": -0.09260411346660431, + "first_commit": "2023-11-06 11:33:47", + "latest_commit": "2023-11-09 18:16:05", + "languages": [], + "model_or_dataset": "model", + "model_size": 9.68, + "model_architectures": "LlamaForCausalLM" + }, + { + "description": "Japanese DialoGPT trained with Aozora (ja) 青空文庫のセリフで���習した日本語のDialoGPT Smallです(en) Japanese DialoGPT Small trained on Aozora Bunko.", + "url": "https://huggingface.co/akiFQC/japanese-dialogpt-small-aozora", + "project_name": "japanese-dialogpt-small-aozora", + "downloads": 18, + "source": "Hugging Face", + "score": -0.09260411346660431, + "first_commit": "2023-02-08 13:22:24", + "latest_commit": "2023-02-09 00:55:31", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "GPT2LMHeadModel" + }, + { + "description": "roberta-large-japanese-aozora-char Model Description", + "url": "https://huggingface.co/KoichiYasuoka/roberta-large-japanese-aozora-char", + "project_name": "roberta-large-japanese-aozora-char", + "downloads": 18, + "source": "Hugging Face", + "score": -0.09260411346660431, + "first_commit": "2021-12-30 14:19:53", + "latest_commit": "2022-06-22 10:22:43", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "RobertaForMaskedLM" + }, + { + "description": "roberta-base-japanese-char-luw-upos Model Description", + "url": "https://huggingface.co/KoichiYasuoka/roberta-base-japanese-char-luw-upos", + "project_name": "roberta-base-japanese-char-luw-upos", + "downloads": 18, + "source": "Hugging Face", + "score": -0.09260411346660431, + "first_commit": "2021-12-28 05:01:56", + "latest_commit": "2024-08-20 18:21:15", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "RobertaForTokenClassification" + }, + { + "description": "JaWiki WikipediaのHTML形式のダンプファイルから抽出したテキストデータセットです。 ", + "url": "https://huggingface.co/datasets/hpprc/jawiki", + "project_name": "jawiki", + "downloads": 18, + "source": "Hugging Face", + "score": -0.09260411346660431, + "first_commit": "2024-02-02 06:36:01", + "latest_commit": "2024-02-13 15:19:49", "languages": [], "model_or_dataset": "dataset", "model_size": null, @@ -11785,7 +12250,7 @@ "project_name": "friendly_JA", "downloads": 17, "source": "Hugging Face", - "score": -0.11417880441139806, + "score": -0.09261471841714064, "first_commit": "2022-01-10 06:31:18", "latest_commit": "2022-05-22 14:57:21", "languages": [], @@ -11799,7 +12264,7 @@ "project_name": "gpt-j-japanese-6.8b", "downloads": 17, "source": "Hugging Face", - "score": -0.11417880441139806, + "score": -0.09261471841714064, "first_commit": "2021-10-17 08:02:54", "latest_commit": "2021-11-10 15:28:57", "languages": [], @@ -11808,18 +12273,32 @@ "model_architectures": "GPTJForCausalLM" }, { - "description": "deberta-base-japanese-unidic Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-unidic", - "project_name": "deberta-base-japanese-unidic", + "description": "roberta-large-japanese-aozora-ud-goeswith Model Description", + "url": "https://huggingface.co/KoichiYasuoka/roberta-large-japanese-aozora-ud-goeswith", + "project_name": "roberta-large-japanese-aozora-ud-goeswith", "downloads": 17, "source": "Hugging Face", - "score": -0.11417880441139806, - "first_commit": "2022-06-08 08:05:33", - "latest_commit": "2022-06-18 23:02:31", + "score": -0.09261471841714064, + "first_commit": "2022-10-15 04:15:39", + "latest_commit": "2024-08-20 18:51:15", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForMaskedLM" + "model_architectures": "RobertaForTokenClassification" + }, + { + "description": "deberta-large-japanese-aozora-ud-goeswith Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-aozora-ud-goeswith", + "project_name": "deberta-large-japanese-aozora-ud-goeswith", + "downloads": 17, + "source": "Hugging Face", + "score": -0.09261471841714064, + "first_commit": "2022-10-14 11:35:36", + "latest_commit": "2024-08-20 19:20:44", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "DebertaV2ForTokenClassification" }, { "description": "Fine-tuned Japanese Wav2Vec2 model for speech recognition using XLSR-53 large Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using Common Voice, JVS and JSUT.", @@ -11827,7 +12306,7 @@ "project_name": "wav2vec2-large-xlsr-53-japanese", "downloads": 17, "source": "Hugging Face", - "score": -0.11417880441139806, + "score": -0.09261471841714064, "first_commit": "2023-05-11 08:47:29", "latest_commit": "2023-05-12 02:15:39", "languages": [], @@ -11836,74 +12315,144 @@ "model_architectures": "Wav2Vec2ForCTC" }, { - "description": "spekulatius マージしているとたまに出てくる「目的の意図とは違うのだけどなんだか消すにはもったいないモデル」をおすそ分けするシリーズです。 ", - "url": "https://huggingface.co/Lasorco/spekulatius", - "project_name": "spekulatius", + "description": "About This model is Lightblue's QLoRA finetune of OpenOrca's Open-Orca/OpenOrcaxOpenChat-Preview2-13B model on Japanese fine-tuning datasets.", + "url": "https://huggingface.co/lightblue/openorca_stx", + "project_name": "openorca_stx", "downloads": 17, "source": "Hugging Face", - "score": -0.11417880441139806, - "first_commit": "2023-10-24 13:56:21", - "latest_commit": "2023-10-26 04:21:35", + "score": -0.09261471841714064, + "first_commit": "2023-09-12 09:29:10", + "latest_commit": "2023-10-02 10:25:36", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": "LlamaForCausalLM" + }, + { + "description": "Cross-Encoder for Natural Language Inference(NLI) for Japanese This model was trained using SentenceTransformers Cross-Encoder class.", + "url": "https://huggingface.co/akiFQC/bert-base-japanese-v3_nli-jsnli-jnli-jsick", + "project_name": "bert-base-japanese-v3_nli-jsnli-jnli-jsick", + "downloads": 17, + "source": "Hugging Face", + "score": -0.09261471841714064, + "first_commit": "2024-04-26 05:15:05", + "latest_commit": "2024-04-26 06:02:55", + "languages": [], + "model_or_dataset": "model", + "model_size": 0.111, + "model_architectures": "BertForSequenceClassification" + }, + { + "description": "gpt2-small-japanese-upos Model Description", + "url": "https://huggingface.co/KoichiYasuoka/gpt2-small-japanese-upos", + "project_name": "gpt2-small-japanese-upos", + "downloads": 17, + "source": "Hugging Face", + "score": -0.09261471841714064, + "first_commit": "2024-06-22 22:28:58", + "latest_commit": "2024-07-27 07:49:34", "languages": [], "model_or_dataset": "model", "model_size": null, + "model_architectures": "GPT2ForTokenClassification" + }, + { + "description": "japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1 japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1 is a merge of the following models: mistralai/Mistral-7B-Instruct-v0.1 stabilityai/japanese-stablelm-instruct-gamma-7b 🧩 Configuration slices: - sources: - model: mistralai/Mistral-7B-Instruct-v0.1 layer_range:", + "url": "https://huggingface.co/MaziyarPanahi/japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1", + "project_name": "japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1", + "downloads": 17, + "source": "Hugging Face", + "score": -0.09261471841714064, + "first_commit": "2024-01-16 12:23:01", + "latest_commit": "2024-01-16 12:27:54", + "languages": [], + "model_or_dataset": "model", + "model_size": 7.24, + "model_architectures": "MistralForCausalLM" + }, + { + "description": "rinna/nekomata-14b-gguf Overview The model is the GGUF version of rinna/nekomata-14b.", + "url": "https://huggingface.co/rinna/nekomata-14b-gguf", + "project_name": "nekomata-14b-gguf", + "downloads": 17, + "source": "Hugging Face", + "score": -0.09261471841714064, + "first_commit": "2023-12-19 08:11:51", + "latest_commit": "2024-07-20 08:29:58", + "languages": [], + "model_or_dataset": "model", + "model_size": 14.2, "model_architectures": null }, { - "description": "はじめに GoogleのGemma-2Bを日本語で使えるように継続事前学習を施した、商用利用可能なベースモデルです。 ", - "url": "https://huggingface.co/alfredplpl/suzume-poc", - "project_name": "suzume-poc", + "description": "rinna/nekomata-7b-gguf Overview The model is the GGUF version of rinna/nekomata-7b.", + "url": "https://huggingface.co/rinna/nekomata-7b-gguf", + "project_name": "nekomata-7b-gguf", "downloads": 17, "source": "Hugging Face", - "score": -0.11417880441139806, - "first_commit": "2024-03-14 09:51:38", - "latest_commit": "2024-03-17 15:05:20", + "score": -0.09261471841714064, + "first_commit": "2023-12-19 08:10:42", + "latest_commit": "2024-07-20 08:36:15", "languages": [], "model_or_dataset": "model", - "model_size": 2.51, - "model_architectures": "GemmaForCausalLM" + "model_size": 7.72, + "model_architectures": null + }, + { + "description": "Chat & support: TheBloke's Discord server Want to contribute?", + "url": "https://huggingface.co/TheBloke/japanese-stablelm-instruct-beta-70B-AWQ", + "project_name": "japanese-stablelm-instruct-beta-70B-AWQ", + "downloads": 17, + "source": "Hugging Face", + "score": -0.09261471841714064, + "first_commit": "2023-11-02 15:45:23", + "latest_commit": "2023-11-09 18:16:16", + "languages": [], + "model_or_dataset": "model", + "model_size": 9.68, + "model_architectures": "LlamaForCausalLM" }, { - "description": "Wav2Vec2-XLS-R-300M-Japanese-Hiragana Fine-tuned facebook/wav2vec2-xls-r-300m on Japanese Hiragana characters using the Common Voice and JSUT.", - "url": "https://huggingface.co/slplab/wav2vec2-xls-r-300m-japanese-hiragana", - "project_name": "wav2vec2-xls-r-300m-japanese-hiragana", + "description": "deberta-base-japanese-wikipedia Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-wikipedia", + "project_name": "deberta-base-japanese-wikipedia", "downloads": 17, "source": "Hugging Face", - "score": -0.11417880441139806, - "first_commit": "2022-09-16 07:34:58", - "latest_commit": "2022-09-16 11:01:54", + "score": -0.09261471841714064, + "first_commit": "2022-06-25 03:46:58", + "latest_commit": "2023-01-27 17:51:51", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "Wav2Vec2ForCTC" + "model_architectures": "DebertaV2ForMaskedLM" }, { - "description": "記事本文からタイトルを生成するモデル SEE: https://qiita.com/sonoisa/items/30876467ad5a8a81821f", - "url": "https://huggingface.co/sonoisa/t5-qiita-title-generation", - "project_name": "t5-qiita-title-generation", + "description": "deberta-base-japanese-luw-upos Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-luw-upos", + "project_name": "deberta-base-japanese-luw-upos", "downloads": 17, "source": "Hugging Face", - "score": -0.11417880441139806, - "first_commit": "2021-10-17 14:46:56", - "latest_commit": "2022-02-21 13:39:01", + "score": -0.09261471841714064, + "first_commit": "2022-05-24 06:55:47", + "latest_commit": "2024-08-20 19:21:57", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "T5ForConditionalGeneration" + "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "bert-japanese-ner このモデルは日本語の固有表現抽出タスクを目的として、京都大学 黒橋・褚・村脇研究室が公開しているBERT日本語Pretrainedモデルをベースにストックマーク株式会社が公開しているner-wikipedia-datasetでファインチューニングしたものです。 ", - "url": "https://huggingface.co/ken11/bert-japanese-ner", - "project_name": "bert-japanese-ner", + "description": "ELECTRA small Japanese finance generator This is a ELECTRA model pretrained on texts in the Japanese language.", + "url": "https://huggingface.co/izumi-lab/electra-small-paper-japanese-fin-generator", + "project_name": "electra-small-paper-japanese-fin-generator", "downloads": 17, "source": "Hugging Face", - "score": -0.11417880441139806, - "first_commit": "2021-11-13 16:28:23", - "latest_commit": "2021-11-14 02:34:01", + "score": -0.09261471841714064, + "first_commit": "2021-10-04 13:38:47", + "latest_commit": "2023-10-21 13:21:24", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForTokenClassification" + "model_size": 0.00491, + "model_architectures": "ElectraForMaskedLM" }, { "description": "Japanese-Vietnamese Translated Sentence Pairs.", @@ -11911,7 +12460,7 @@ "project_name": "ja_vi_translation", "downloads": 17, "source": "Hugging Face", - "score": -0.11417880441139806, + "score": -0.09261471841714064, "first_commit": "2024-03-13 17:52:50", "latest_commit": "2024-04-08 19:35:06", "languages": [], @@ -11920,18 +12469,18 @@ "model_architectures": null }, { - "description": "roberta-base-japanese-aozora Model Description", - "url": "https://huggingface.co/KoichiYasuoka/roberta-base-japanese-aozora", - "project_name": "roberta-base-japanese-aozora", - "downloads": 16, + "description": "This dataset is a collection of Korean, Chinese, and Japanese OpenOrca translation datasets.", + "url": "https://huggingface.co/datasets/werty1248/OpenOrca-EnKoZhJa-18k", + "project_name": "OpenOrca-EnKoZhJa-18k", + "downloads": 17, "source": "Hugging Face", - "score": -0.11419451576809228, - "first_commit": "2021-12-21 00:04:03", - "latest_commit": "2022-10-15 14:20:11", + "score": -0.09261471841714064, + "first_commit": "2024-08-10 18:54:09", + "latest_commit": "2024-08-10 19:16:35", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "RobertaForMaskedLM" + "model_architectures": null }, { "description": "deberta-base-japanese-unidic-luw-upos Model Description", @@ -11939,7 +12488,7 @@ "project_name": "deberta-base-japanese-unidic-luw-upos", "downloads": 16, "source": "Hugging Face", - "score": -0.11419451576809228, + "score": -0.09262532336767697, "first_commit": "2022-06-08 08:26:25", "latest_commit": "2024-08-20 20:15:13", "languages": [], @@ -11948,60 +12497,46 @@ "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "モデル説明 (model explanation) YaguruMagiku 0.6 : AbyssOrangeMix2_sfw 0.4 マージ元のルーツにNAIリークが含まれるという噂があるので、NAIリークアンチには非推奨 理想の黒髪ポニテ顔が出せるYaguruMagikuを、ある程度顔が近くて制御しやすいAbyssOrangeMix2と混ぜてみた。 ", - "url": "https://huggingface.co/ThePioneer/MoeDiffusion", - "project_name": "MoeDiffusion", + "description": "line-corporation/japanese-large-lm-3.6b line-corporationさんが公開しているjapanese-large-lm-3.6bのgguf変換版です。 ", + "url": "https://huggingface.co/mmnga/line-corp-japanese-large-lm-3.6b-gguf", + "project_name": "line-corp-japanese-large-lm-3.6b-gguf", "downloads": 16, "source": "Hugging Face", - "score": -0.11419451576809228, - "first_commit": "2023-01-18 11:14:31", - "latest_commit": "2023-01-21 02:10:41", + "score": -0.09262532336767697, + "first_commit": "2023-09-02 18:18:41", + "latest_commit": "2023-09-08 02:53:05", "languages": [], "model_or_dataset": "model", "model_size": null, "model_architectures": null }, { - "description": "transformer-lm-japanese-0.1b", - "url": "https://huggingface.co/fukugawa/transformer-lm-japanese-0.1b", - "project_name": "transformer-lm-japanese-0.1b", + "description": "日本語でtrainingしたllama2 model size: 417.12M trainingは以下のscript参照https://github.com/Lightning-AI/lit-gpt/tree/main use from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained(\"if001/sentencepiece_ja\", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained(\"if001/llama2_ja_small\")", + "url": "https://huggingface.co/if001/llama2_ja_small", + "project_name": "llama2_ja_small", "downloads": 16, "source": "Hugging Face", - "score": -0.11419451576809228, - "first_commit": "2023-07-12 02:11:11", - "latest_commit": "2024-06-03 06:17:19", + "score": -0.09262532336767697, + "first_commit": "2023-10-11 09:11:41", + "latest_commit": "2023-10-14 13:50:54", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "TransformerLMForCausalLM" - }, - { - "description": "japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1 japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1 is a merge of the following models: mistralai/Mistral-7B-Instruct-v0.1 stabilityai/japanese-stablelm-base-gamma-7b 🧩 Configuration slices: - sources: - model: mistralai/Mistral-7B-Instruct-v0.1 layer_range:", - "url": "https://huggingface.co/MaziyarPanahi/japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1", - "project_name": "japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1", - "downloads": 16, - "source": "Hugging Face", - "score": -0.11419451576809228, - "first_commit": "2024-01-17 04:41:20", - "latest_commit": "2024-01-17 04:46:18", - "languages": [], - "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": "MistralForCausalLM" + "model_architectures": "LlamaForCausalLM" }, { - "description": "Chat-Vector-LLaVA-v1.5-7b-JA Model Card Model detail Model type: Chat-Vector-LLaVA-v1.5-7b-JA is a vision-language model that can converse about input images in Japanese.", - "url": "https://huggingface.co/toshi456/chat-vector-llava-v1.5-7b-ja", - "project_name": "chat-vector-llava-v1.5-7b-ja", + "description": "gpt2-large-japanese-ud-causal Model Description", + "url": "https://huggingface.co/KoichiYasuoka/gpt2-large-japanese-ud-causal", + "project_name": "gpt2-large-japanese-ud-causal", "downloads": 16, "source": "Hugging Face", - "score": -0.11419451576809228, - "first_commit": "2024-05-06 04:07:19", - "latest_commit": "2024-05-06 11:33:32", + "score": -0.09262532336767697, + "first_commit": "2024-08-25 00:35:43", + "latest_commit": "2024-08-29 17:08:21", "languages": [], "model_or_dataset": "model", - "model_size": 7.06, - "model_architectures": "LlavaLlamaForCausalLM" + "model_size": null, + "model_architectures": "GPT2ForTokenClassification" }, { "description": "Model Card for Model ID MMedBench and KoreanMedMCQA Instruction Fine-Tuned Multilingual Llama3 8B 4Bit quantized model using QLoRA.", @@ -12009,7 +12544,7 @@ "project_name": "MLMedLlama3", "downloads": 16, "source": "Hugging Face", - "score": -0.11419451576809228, + "score": -0.09262532336767697, "first_commit": "2024-08-20 17:08:05", "latest_commit": "2024-08-28 15:39:15", "languages": [], @@ -12018,348 +12553,278 @@ "model_architectures": "LlamaForCausalLM" }, { - "description": "Cross-Encoder for Natural Language Inference(NLI) for Japanese This model was trained using SentenceTransformers Cross-Encoder class.", - "url": "https://huggingface.co/akiFQC/bert-base-japanese-v3_nli-jsnli-jnli-jsick", - "project_name": "bert-base-japanese-v3_nli-jsnli-jnli-jsick", - "downloads": 16, - "source": "Hugging Face", - "score": -0.11419451576809228, - "first_commit": "2024-04-26 05:15:05", - "latest_commit": "2024-04-26 06:02:55", - "languages": [], - "model_or_dataset": "model", - "model_size": 0.111, - "model_architectures": "BertForSequenceClassification" - }, - { - "description": "Chat & support: TheBloke's Discord server Want to contribute?", - "url": "https://huggingface.co/TheBloke/japanese-stablelm-instruct-gamma-7B-GPTQ", - "project_name": "japanese-stablelm-instruct-gamma-7B-GPTQ", + "description": "ELYZA-japanese-Llama-2-fast-MoE-2x7B-v0.1-GGUF 概要 Aratako/ELYZA-japanese-Llama-2-fast-MoE-2x7B-v0.1の量子化済みGGUF版です。", + "url": "https://huggingface.co/Aratako/ELYZA-japanese-Llama-2-fast-MoE-2x7B-v0.1-GGUF", + "project_name": "ELYZA-japanese-Llama-2-fast-MoE-2x7B-v0.1-GGUF", "downloads": 16, "source": "Hugging Face", - "score": -0.11419451576809228, - "first_commit": "2023-10-28 19:03:17", - "latest_commit": "2023-10-28 20:24:40", + "score": -0.09262532336767697, + "first_commit": "2024-03-07 13:21:38", + "latest_commit": "2024-03-07 13:47:58", "languages": [], "model_or_dataset": "model", - "model_size": 1.2, - "model_architectures": "MistralForCausalLM" + "model_size": 11.2, + "model_architectures": null }, { - "description": "Japanese GPT2 Lyric Model Model description", - "url": "https://huggingface.co/skytnt/gpt2-japanese-lyric-medium", - "project_name": "gpt2-japanese-lyric-medium", + "description": "nlp-waseda/gpt2-small-japanese This model is Japanese GPT-2 pretrained on Japanese Wikipedia and CC-100.", + "url": "https://huggingface.co/nlp-waseda/gpt2-small-japanese", + "project_name": "gpt2-small-japanese", "downloads": 16, "source": "Hugging Face", - "score": -0.11419451576809228, - "first_commit": "2022-07-08 13:28:12", - "latest_commit": "2023-10-21 14:53:57", + "score": -0.09262532336767697, + "first_commit": "2022-03-30 03:34:11", + "latest_commit": "2022-03-30 04:28:17", "languages": [], "model_or_dataset": "model", - "model_size": 0.361, + "model_size": null, "model_architectures": "GPT2LMHeadModel" }, { - "description": "It covers multiple fields such as tourism, medical treatment, daily life, news, etc. ", - "url": "https://huggingface.co/datasets/Nexdata/English-Japanese_Parallel_Corpus_Data", - "project_name": "English-Japanese_Parallel_Corpus_Data", + "description": "This is a Japanese sentence-T5 model.", + "url": "https://huggingface.co/sonoisa/sentence-t5-base-ja-mean-tokens", + "project_name": "sentence-t5-base-ja-mean-tokens", "downloads": 16, "source": "Hugging Face", - "score": -0.11419451576809228, - "first_commit": "2023-11-08 10:47:40", - "latest_commit": "2024-08-05 03:14:27", - "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null - }, - { - "description": "Mistral-Nemo-Japanese-Instruct-2408 Model Description", - "url": "https://huggingface.co/cyberagent/Mistral-Nemo-Japanese-Instruct-2408", - "project_name": "Mistral-Nemo-Japanese-Instruct-2408", - "downloads": 15, - "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2024-08-30 03:57:43", - "latest_commit": "2024-08-30 04:03:41", - "languages": [], - "model_or_dataset": "model", - "model_size": 12.2, - "model_architectures": "MistralForCausalLM" - }, - { - "description": "gpt2-small-japanese-ud-causal Model Description", - "url": "https://huggingface.co/KoichiYasuoka/gpt2-small-japanese-ud-causal", - "project_name": "gpt2-small-japanese-ud-causal", - "downloads": 15, - "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2024-08-22 13:33:02", - "latest_commit": "2024-08-25 17:54:09", + "score": -0.09262532336767697, + "first_commit": "2021-12-27 11:57:10", + "latest_commit": "2022-07-31 07:54:13", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "GPT2ForTokenClassification" + "model_architectures": "T5Model" }, { - "description": "Japanese Stable LM Instruct Gamma 7B Model Description", - "url": "https://huggingface.co/LoneStriker/stabilityai_japanese-stablelm-instruct-gamma-7b-3.0bpw-h6-exl2", - "project_name": "stabilityai_japanese-stablelm-instruct-gamma-7b-3.0bpw-h6-exl2", - "downloads": 15, + "description": "bert-japanese-ner このモデルは日本語の固有表現抽出タスクを目的として、京都大学 黒橋・褚・村脇研究室が公開しているBERT日本語Pretrainedモデルをベースにストックマーク株式会社が公開しているner-wikipedia-datasetでファインチューニングしたものです。 ", + "url": "https://huggingface.co/ken11/bert-japanese-ner", + "project_name": "bert-japanese-ner", + "downloads": 16, "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2023-10-28 20:16:15", - "latest_commit": "2023-10-28 15:16:25", + "score": -0.09262532336767697, + "first_commit": "2021-11-13 16:28:23", + "latest_commit": "2021-11-14 02:34:01", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "MistralForCausalLM" - }, - { - "description": "ELYZA-japanese-Llama-2-13b-fast-instruct-gguf ELYZA-japanese-Llama-2-13b-fast-instructの GGUF 変換モデルです。", - "url": "https://huggingface.co/schroneko/ELYZA-japanese-Llama-2-13b-fast-instruct-gguf", - "project_name": "ELYZA-japanese-Llama-2-13b-fast-instruct-gguf", - "downloads": 15, - "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2024-01-23 14:14:39", - "latest_commit": "2024-01-25 06:30:57", - "languages": [], - "model_or_dataset": "model", - "model_size": 13.1, - "model_architectures": null - }, - { - "description": "ELYZA-japanese-Llama-2-fast-MoE-2x7B-v0.1-GGUF 概要 Aratako/ELYZA-japanese-Llama-2-fast-MoE-2x7B-v0.1の量子化済みGGUF版です。", - "url": "https://huggingface.co/Aratako/ELYZA-japanese-Llama-2-fast-MoE-2x7B-v0.1-GGUF", - "project_name": "ELYZA-japanese-Llama-2-fast-MoE-2x7B-v0.1-GGUF", - "downloads": 15, - "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2024-03-07 13:21:38", - "latest_commit": "2024-03-07 13:47:58", - "languages": [], - "model_or_dataset": "model", - "model_size": 11.2, - "model_architectures": null + "model_architectures": "BertForTokenClassification" }, { - "description": "SambaLingo-Japanese-Chat SambaLingo-Japanese-Chat is a human aligned chat model trained in Japanese and English.", - "url": "https://huggingface.co/LoneStriker/SambaLingo-Japanese-Chat-3.0bpw-h6-exl2", - "project_name": "SambaLingo-Japanese-Chat-3.0bpw-h6-exl2", - "downloads": 15, + "description": "roberta-small-japanese-aozora-char Model Description", + "url": "https://huggingface.co/KoichiYasuoka/roberta-small-japanese-aozora-char", + "project_name": "roberta-small-japanese-aozora-char", + "downloads": 16, "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2024-03-07 06:50:19", - "latest_commit": "2024-03-07 06:51:42", + "score": -0.09262532336767697, + "first_commit": "2021-12-23 02:38:26", + "latest_commit": "2021-12-23 11:55:42", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "LlamaForCausalLM" + "model_architectures": "RobertaForMaskedLM" }, { - "description": "Llama-3-8B-Instruct-JP-nk2t-v0.3 Model Details: Built with Meta Llama 3 llama-3-8bの日本語継続学習モデルにChatVectorを適用し、さらにQLoraでファインチューニングしたモデルです。 ", - "url": "https://huggingface.co/nk2t/Llama-3-8B-Instruct-japanese-nk2t-v0.3", - "project_name": "Llama-3-8B-Instruct-japanese-nk2t-v0.3", + "description": "deberta-large-japanese-luw-upos Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-luw-upos", + "project_name": "deberta-large-japanese-luw-upos", "downloads": 15, "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2024-05-15 12:24:06", - "latest_commit": "2024-05-22 11:02:28", + "score": -0.09263592831821331, + "first_commit": "2022-05-26 14:52:32", + "latest_commit": "2023-01-14 23:15:30", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "LlamaForCausalLM" + "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "zenz-v2 zenz-v2はGPT-2アーキテクチャに基づくかな漢字変換タスクに特化した言語モデルです。", - "url": "https://huggingface.co/Miwa-Keita/zenz-v2-gguf", - "project_name": "zenz-v2-gguf", + "description": "Barba Barba is a multilingual natural language inference model for textual entailment and zero-shot text classification, available as an end-to-end service through TensorFlow Serving.", + "url": "https://huggingface.co/hyperonym/barba", + "project_name": "barba", "downloads": 15, "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2024-07-31 15:15:16", - "latest_commit": "2024-08-04 09:35:48", + "score": -0.09263592831821331, + "first_commit": "2023-04-29 06:27:12", + "latest_commit": "2023-04-29 13:45:12", "languages": [], "model_or_dataset": "model", - "model_size": 0.09509999999999999, - "model_architectures": null + "model_size": null, + "model_architectures": "XLMRobertaForSequenceClassification" }, { - "description": "gpt2-large-japanese-ud-causal Model Description", - "url": "https://huggingface.co/KoichiYasuoka/gpt2-large-japanese-ud-causal", - "project_name": "gpt2-large-japanese-ud-causal", + "description": "こちらでアップロードできないので、civitaiにて先に公開しています。 ", + "url": "https://huggingface.co/sazyou-roukaku/AfterRealXL", + "project_name": "AfterRealXL", "downloads": 15, "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2024-08-25 00:35:43", - "latest_commit": "2024-08-29 17:08:21", + "score": -0.09263592831821331, + "first_commit": "2023-09-23 08:43:02", + "latest_commit": "2023-10-01 18:12:09", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "GPT2ForTokenClassification" + "model_architectures": null }, { - "description": "japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1 japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1 is a merge of the following models: mistralai/Mistral-7B-Instruct-v0.1 stabilityai/japanese-stablelm-instruct-gamma-7b 🧩 Configuration slices: - sources: - model: mistralai/Mistral-7B-Instruct-v0.1 layer_range:", - "url": "https://huggingface.co/MaziyarPanahi/japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1", - "project_name": "japanese-stablelm-instruct-gamma-7b-Mistral-7B-Instruct-v0.1", + "description": "youhansun/Llama-3-70B-japanese-suzume-vector-v0.1-Q2_K-GGUF", + "url": "https://huggingface.co/youhansun/Llama-3-70B-japanese-suzume-vector-v0.1-Q2_K-GGUF", + "project_name": "Llama-3-70B-japanese-suzume-vector-v0.1-Q2_K-GGUF", "downloads": 15, "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2024-01-16 12:23:01", - "latest_commit": "2024-01-16 12:27:54", + "score": -0.09263592831821331, + "first_commit": "2024-06-02 04:49:31", + "latest_commit": "2024-06-02 04:52:45", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": "MistralForCausalLM" + "model_size": 70.6, + "model_architectures": null }, { - "description": "Shisa 7B Shisa 7B (shisa-7b-v1)", - "url": "https://huggingface.co/LoneStriker/shisa-7b-v1-3.0bpw-h6-exl2", - "project_name": "shisa-7b-v1-3.0bpw-h6-exl2", + "description": "Mixtral-8x7B-Instruct-v0.1-japanese Mixtral-8x7B-Instruct-v0.1-japaneseはMixtral-8x7B-Instruct-v0.1をベースに日本語の語彙拡張継続事前学習を実施したモデルです。", + "url": "https://huggingface.co/abeja/Mixtral-8x7B-Instruct-v0.1-japanese", + "project_name": "Mixtral-8x7B-Instruct-v0.1-japanese", "downloads": 15, "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2023-12-07 17:52:29", - "latest_commit": "2023-12-07 18:54:23", + "score": -0.09263592831821331, + "first_commit": "2024-04-17 02:56:15", + "latest_commit": "2024-04-20 09:14:27", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "MistralForCausalLM" + "model_size": 46.9, + "model_architectures": "MixtralForCausalLM" }, { - "description": "whisper-large-v2-jp model for CTranslate2 This repository contains the conversion of vumichien/whisper-large-v2-jp to the CTranslate2 model format.", - "url": "https://huggingface.co/arc-r/faster-whisper-large-v2-jp", - "project_name": "faster-whisper-large-v2-jp", + "description": "japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1 japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1 is a merge of the following models: mistralai/Mistral-7B-Instruct-v0.1 stabilityai/japanese-stablelm-base-gamma-7b 🧩 Configuration slices: - sources: - model: mistralai/Mistral-7B-Instruct-v0.1 layer_range:", + "url": "https://huggingface.co/MaziyarPanahi/japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1", + "project_name": "japanese-stablelm-base-gamma-7b-Mistral-7B-Instruct-v0.1", "downloads": 15, "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2023-07-07 06:16:06", - "latest_commit": "2023-07-07 18:09:09", + "score": -0.09263592831821331, + "first_commit": "2024-01-17 04:41:20", + "latest_commit": "2024-01-17 04:46:18", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": null + "model_size": 7.24, + "model_architectures": "MistralForCausalLM" }, { - "description": "ku-accms/bert-base-japanese-ssuw Model description This is a pre-trained Japanese BERT base model for super short unit words (SSUW).", - "url": "https://huggingface.co/ku-accms/bert-base-japanese-ssuw", - "project_name": "bert-base-japanese-ssuw", + "description": "Chat & support: TheBloke's Discord server Want to contribute?", + "url": "https://huggingface.co/TheBloke/japanese-stablelm-instruct-beta-70B-GPTQ", + "project_name": "japanese-stablelm-instruct-beta-70B-GPTQ", "downloads": 15, "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2023-04-11 13:57:30", - "latest_commit": "2023-04-12 04:40:42", + "score": -0.09263592831821331, + "first_commit": "2023-11-02 15:45:24", + "latest_commit": "2023-11-02 20:04:07", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForMaskedLM" + "model_size": 9.1, + "model_architectures": "LlamaForCausalLM" }, { - "description": "japanese-gpt2-medium-unidic This is a medium-sized Japanese GPT-2 model using BERT-like tokenizer.", - "url": "https://huggingface.co/okazaki-lab/japanese-gpt2-medium-unidic", - "project_name": "japanese-gpt2-medium-unidic", + "description": "Model Card for Japanese DeBERTa V2 base Model description This is a Japanese DeBERTa V2 base model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.", + "url": "https://huggingface.co/ku-nlp/deberta-v2-base-japanese-with-auto-jumanpp", + "project_name": "deberta-v2-base-japanese-with-auto-jumanpp", "downloads": 15, "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2023-02-27 05:42:22", - "latest_commit": "2023-03-22 06:22:32", + "score": -0.09263592831821331, + "first_commit": "2023-09-07 06:04:29", + "latest_commit": "2023-11-20 06:00:08", "languages": [], "model_or_dataset": "model", - "model_size": 0.362, - "model_architectures": "GPT2LMHeadModel" + "model_size": 0.137, + "model_architectures": "DebertaV2ForMaskedLM" }, { - "description": "deberta-base-japanese-wikipedia-luw-upos Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-wikipedia-luw-upos", - "project_name": "deberta-base-japanese-wikipedia-luw-upos", + "description": "bart-large-japanese This model is converted from the original Japanese BART Pretrained model released by Kyoto University.", + "url": "https://huggingface.co/Formzu/bart-large-japanese", + "project_name": "bart-large-japanese", "downloads": 15, "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2022-06-25 06:28:11", - "latest_commit": "2024-08-20 17:53:34", + "score": -0.09263592831821331, + "first_commit": "2022-10-31 06:53:19", + "latest_commit": "2022-11-07 12:06:32", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForTokenClassification" + "model_architectures": "MBartForConditionalGeneration" }, { - "description": "japanese-soseki-gpt2-1b", - "url": "https://huggingface.co/jweb/japanese-soseki-gpt2-1b", - "project_name": "japanese-soseki-gpt2-1b", + "description": "Japanese Stable Diffusion Pokemon Model Card Stable-Diffusion-Pokemon-ja is a Japanese-specific latent text-to-image diffusion model capable of generating Pokemon images given any text input.", + "url": "https://huggingface.co/svjack/Stable-Diffusion-Pokemon-ja", + "project_name": "Stable-Diffusion-Pokemon-ja", "downloads": 15, "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2022-03-03 04:53:15", - "latest_commit": "2023-03-27 12:09:04", + "score": -0.09263592831821331, + "first_commit": "2022-10-30 08:19:13", + "latest_commit": "2023-05-16 09:23:49", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "GPT2LMHeadModel" + "model_architectures": null }, { - "description": "タイトルから記事本文を生成するモデル SEE: https://qiita.com/sonoisa/items/a9af64ff641f0bbfed44", - "url": "https://huggingface.co/sonoisa/t5-base-japanese-article-generation", - "project_name": "t5-base-japanese-article-generation", + "description": "ku-nlp/roberta-large-japanese-char-wwm Model description This is a Japanese RoBERTa large model pre-trained on Japanese Wikipedia and the Japanese portion of CC-100.", + "url": "https://huggingface.co/ku-nlp/roberta-large-japanese-char-wwm", + "project_name": "roberta-large-japanese-char-wwm", "downloads": 15, "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2021-04-03 13:55:25", - "latest_commit": "2024-04-17 11:39:12", + "score": -0.09263592831821331, + "first_commit": "2022-09-18 08:10:44", + "latest_commit": "2023-03-19 01:58:12", "languages": [], "model_or_dataset": "model", - "model_size": 0.223, - "model_architectures": "T5ForConditionalGeneration" + "model_size": 0.323, + "model_architectures": "RobertaForMaskedLM" }, { - "description": "TinySlime-1.1B-Chat-v1.0 TinySlime は日本語に特化した小規模言語モデルです。 ", - "url": "https://huggingface.co/2121-8/TinySlime-1.1B-Chat-v1.0", - "project_name": "TinySlime-1.1B-Chat-v1.0", + "description": "Google's mt5-base fine-tuned in Japanese to summarize patent claims in a limited Pharmaceutical domain. ", + "url": "https://huggingface.co/kz/mt5base-finetuned-patentsum-japanese-small", + "project_name": "mt5base-finetuned-patentsum-japanese-small", "downloads": 15, "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2024-07-02 03:34:30", - "latest_commit": "2024-07-02 08:53:11", + "score": -0.09263592831821331, + "first_commit": "2021-04-10 00:31:15", + "latest_commit": "2022-05-19 06:50:32", "languages": [], "model_or_dataset": "model", - "model_size": 1.1, - "model_architectures": "LlamaForCausalLM" + "model_size": null, + "model_architectures": "MT5ForConditionalGeneration" }, { - "description": "モデルについて Qwen/Qwen1.5-0.5Bを日英データ5Bトークンで継続事前学習したモデルです。 ", - "url": "https://huggingface.co/Kendamarron/Tokara-0.5B-v0.1", - "project_name": "Tokara-0.5B-v0.1", + "description": "ELECTRA small Japanese generator This is a ELECTRA model pretrained on texts in the Japanese language.", + "url": "https://huggingface.co/izumi-lab/electra-small-paper-japanese-generator", + "project_name": "electra-small-paper-japanese-generator", "downloads": 15, "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2024-05-06 11:39:26", - "latest_commit": "2024-05-08 12:44:05", + "score": -0.09263592831821331, + "first_commit": "2021-10-04 13:47:24", + "latest_commit": "2023-10-21 13:21:31", "languages": [], "model_or_dataset": "model", - "model_size": 0.464, - "model_architectures": "Qwen2ForCausalLM" + "model_size": 0.00491, + "model_architectures": "ElectraForMaskedLM" }, { - "description": "自動生成Q&A 種々のデータソースから､MaziyarPanahi/Mixtral-8x22B-Instruct-v0.1-GGUFを使ってQ&Aを自動生成したものです｡ CC-BY系またはApatch-2.0のデータソースを改変して生成しています。 ", - "url": "https://huggingface.co/datasets/hatakeyama-llm-team/AutoGeneratedJapaneseQA", - "project_name": "AutoGeneratedJapaneseQA", + "description": "ELECTRA small Japanese generator This is a ELECTRA model pretrained on texts in the Japanese language.", + "url": "https://huggingface.co/izumi-lab/electra-small-japanese-generator", + "project_name": "electra-small-japanese-generator", "downloads": 15, "source": "Hugging Face", - "score": -0.1142102271247865, - "first_commit": "2024-04-27 04:32:20", - "latest_commit": "2024-05-19 03:22:08", + "score": -0.09263592831821331, + "first_commit": "2021-10-04 13:43:37", + "latest_commit": "2023-10-21 13:21:28", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null + "model_or_dataset": "model", + "model_size": 0.013800000000000002, + "model_architectures": "ElectraForMaskedLM" }, { "description": "BERT base Japanese model This repository contains a BERT base model trained on Japanese Wikipedia dataset.", "url": "https://huggingface.co/colorfulscoop/bert-base-ja", "project_name": "bert-base-ja", - "downloads": 14, + "downloads": 15, "source": "Hugging Face", - "score": -0.11422593848148072, + "score": -0.09263592831821331, "first_commit": "2021-07-30 10:11:35", "latest_commit": "2021-09-23 15:46:05", "languages": [], @@ -12368,186 +12833,172 @@ "model_architectures": "BertForPreTraining" }, { - "description": "nlp-waseda/gpt2-small-japanese-wikipedia This model is Japanese GPT-2 pretrained on Japanese Wikipedia.", - "url": "https://huggingface.co/nlp-waseda/gpt2-small-japanese-wikipedia", - "project_name": "gpt2-small-japanese-wikipedia", - "downloads": 14, - "source": "Hugging Face", - "score": -0.11422593848148072, - "first_commit": "2021-12-28 01:22:40", - "latest_commit": "2021-12-28 15:31:38", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "GPT2LMHeadModel" - }, - { - "description": "deberta-large-japanese-aozora-ud-head Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-aozora-ud-head", - "project_name": "deberta-large-japanese-aozora-ud-head", - "downloads": 14, + "description": "JP Voice-Text Dataset for", + "url": "https://huggingface.co/datasets/deepghs/fgo_voices_jp", + "project_name": "fgo_voices_jp", + "downloads": 15, "source": "Hugging Face", - "score": -0.11422593848148072, - "first_commit": "2022-06-17 15:00:25", - "latest_commit": "2023-03-04 20:17:12", + "score": -0.09263592831821331, + "first_commit": "2024-08-28 08:56:04", + "latest_commit": "2024-08-28 09:14:22", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "DebertaV2ForQuestionAnswering" + "model_architectures": null }, { - "description": "このモデルはdeberta-v2-base-japaneseをファインチューニングして固有表現抽出（NER）に用いれるようにしたものです。 ", - "url": "https://huggingface.co/Mizuiro-sakura/deberta-v2-base-japanese-finetuned-ner", - "project_name": "deberta-v2-base-japanese-finetuned-ner", + "description": "NLLB-200 1.3B fine-tuned on Ascendance of a Bookworm", + "url": "https://huggingface.co/thefrigidliquidation/nllb-200-distilled-1.3B-bookworm", + "project_name": "nllb-200-distilled-1.3B-bookworm", "downloads": 14, "source": "Hugging Face", - "score": -0.11422593848148072, - "first_commit": "2023-01-20 05:57:37", - "latest_commit": "2023-03-27 08:05:06", + "score": -0.09264653326874964, + "first_commit": "2022-07-27 20:39:08", + "latest_commit": "2024-04-14 18:45:22", "languages": [], "model_or_dataset": "model", - "model_size": 0.112, - "model_architectures": "DebertaV2ForTokenClassification" + "model_size": 1.37, + "model_architectures": "M2M100ForConditionalGeneration" }, { - "description": "このモデルはdeberta-v2-tiny-japaneseをファインチューニングしてQAタスクに用いれるようにしたものです。 ", - "url": "https://huggingface.co/Mizuiro-sakura/deberta-v2-tiny-japanese-finetuned-QA", - "project_name": "deberta-v2-tiny-japanese-finetuned-QA", + "description": "(English part follows Japanese one.", + "url": "https://huggingface.co/tohoku-nlp/stable-diffusion-xl-jp-base-1.0", + "project_name": "stable-diffusion-xl-jp-base-1.0", "downloads": 14, "source": "Hugging Face", - "score": -0.11422593848148072, - "first_commit": "2023-05-11 10:34:38", - "latest_commit": "2023-05-11 10:38:32", + "score": -0.09264653326874964, + "first_commit": "2023-11-06 05:02:27", + "latest_commit": "2023-11-06 05:37:01", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForQuestionAnswering" + "model_architectures": null }, { - "description": "Model Card for Japanese DeBERTa V2 base Model description This is a Japanese DeBERTa V2 base model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.", - "url": "https://huggingface.co/ku-nlp/deberta-v2-base-japanese-with-auto-jumanpp", - "project_name": "deberta-v2-base-japanese-with-auto-jumanpp", + "description": "Shisa 7B Shisa 7B (shisa-7b-v1)", + "url": "https://huggingface.co/LoneStriker/shisa-7b-v1-3.0bpw-h6-exl2", + "project_name": "shisa-7b-v1-3.0bpw-h6-exl2", "downloads": 14, "source": "Hugging Face", - "score": -0.11422593848148072, - "first_commit": "2023-09-07 06:04:29", - "latest_commit": "2023-11-20 06:00:08", + "score": -0.09264653326874964, + "first_commit": "2023-12-07 17:52:29", + "latest_commit": "2023-12-07 18:54:23", "languages": [], "model_or_dataset": "model", - "model_size": 0.137, - "model_architectures": "DebertaV2ForMaskedLM" + "model_size": null, + "model_architectures": "MistralForCausalLM" }, { - "description": "COMET-GPT2 ja v2 Finetuned GPT-2 xl on the large version of ATOMIC ja using a causal language modeling (CLM) objective.", - "url": "https://huggingface.co/nlp-waseda/comet-gpt2-xl-japanese", - "project_name": "comet-gpt2-xl-japanese", + "description": "This model was created by merging intfloat/e5-mistral-7b-instruct and stabilityai/japanese-stablelm-base-gamma-7b.", + "url": "https://huggingface.co/oshizo/japanese-e5-mistral-7b_slerp", + "project_name": "japanese-e5-mistral-7b_slerp", "downloads": 14, "source": "Hugging Face", - "score": -0.11422593848148072, - "first_commit": "2023-09-26 13:37:52", - "latest_commit": "2024-03-11 04:16:02", + "score": -0.09264653326874964, + "first_commit": "2024-01-04 12:33:19", + "latest_commit": "2024-01-05 15:48:24", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "GPT2LMHeadModel" + "model_size": 7.24, + "model_architectures": "MistralModel" }, { - "description": "ELYZA-japanese-Llama-2-MoE-2x13B-v0.1-GGUF 概要 Aratako/ELYZA-japanese-Llama-2-MoE-2x13B-v0.1の量子化済みGGUF版です。", - "url": "https://huggingface.co/Aratako/ELYZA-japanese-Llama-2-MoE-2x13B-v0.1-GGUF", - "project_name": "ELYZA-japanese-Llama-2-MoE-2x13B-v0.1-GGUF", + "description": "SpiralAI Spiral-RetNet-3b-base We have conducted pre-training from scratch on the RetNet (https://arxiv.org/abs/2307.08621)", + "url": "https://huggingface.co/Spiral-AI/Spiral-RetNet-3b-base", + "project_name": "Spiral-RetNet-3b-base", "downloads": 14, "source": "Hugging Face", - "score": -0.11422593848148072, - "first_commit": "2024-03-03 12:51:40", - "latest_commit": "2024-03-03 13:39:01", + "score": -0.09264653326874964, + "first_commit": "2024-04-30 09:33:26", + "latest_commit": "2024-05-01 04:54:26", "languages": [], "model_or_dataset": "model", - "model_size": 21.5, - "model_architectures": null + "model_size": 2.86, + "model_architectures": "RetNetForCausalLM" }, { - "description": "SambaLingo-Japanese-Chat SambaLingo-Japanese-Chat is a human aligned chat model trained in Japanese and English.", - "url": "https://huggingface.co/LoneStriker/SambaLingo-Japanese-Chat-5.0bpw-h6-exl2", - "project_name": "SambaLingo-Japanese-Chat-5.0bpw-h6-exl2", + "description": "はじめに GoogleのGemma-2Bを日本語で使えるように継続事前学習を施した、商用利用可能なベースモデルです。 ", + "url": "https://huggingface.co/alfredplpl/suzume-poc", + "project_name": "suzume-poc", "downloads": 14, "source": "Hugging Face", - "score": -0.11422593848148072, - "first_commit": "2024-03-07 06:53:27", - "latest_commit": "2024-03-07 06:55:27", + "score": -0.09264653326874964, + "first_commit": "2024-03-14 09:51:38", + "latest_commit": "2024-03-17 15:05:20", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LlamaForCausalLM" + "model_size": 2.51, + "model_architectures": "GemmaForCausalLM" }, { - "description": "gpt2-large-japanese-upos Model Description", - "url": "https://huggingface.co/KoichiYasuoka/gpt2-large-japanese-upos", - "project_name": "gpt2-large-japanese-upos", + "description": "Japanese Stable LM Instruct Gamma 7B Model Description", + "url": "https://huggingface.co/LoneStriker/stabilityai_japanese-stablelm-instruct-gamma-7b-3.0bpw-h6-exl2", + "project_name": "stabilityai_japanese-stablelm-instruct-gamma-7b-3.0bpw-h6-exl2", "downloads": 14, "source": "Hugging Face", - "score": -0.11422593848148072, - "first_commit": "2024-06-22 22:44:06", - "latest_commit": "2024-07-27 07:49:47", + "score": -0.09264653326874964, + "first_commit": "2023-10-28 20:16:15", + "latest_commit": "2023-10-28 15:16:25", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "GPT2ForTokenClassification" + "model_architectures": "MistralForCausalLM" }, { - "description": "bart-large-japanese This model is converted from the original Japanese BART Pretrained model released by Kyoto University.", - "url": "https://huggingface.co/Formzu/bart-large-japanese", - "project_name": "bart-large-japanese", + "description": "ku-accms/bert-base-japanese-ssuw Model description This is a pre-trained Japanese BERT base model for super short unit words (SSUW).", + "url": "https://huggingface.co/ku-accms/bert-base-japanese-ssuw", + "project_name": "bert-base-japanese-ssuw", "downloads": 14, "source": "Hugging Face", - "score": -0.11422593848148072, - "first_commit": "2022-10-31 06:53:19", - "latest_commit": "2022-11-07 12:06:32", + "score": -0.09264653326874964, + "first_commit": "2023-04-11 13:57:30", + "latest_commit": "2023-04-12 04:40:42", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "MBartForConditionalGeneration" + "model_architectures": "BertForMaskedLM" }, { - "description": "ku-nlp/roberta-large-japanese-char-wwm Model description This is a Japanese RoBERTa large model pre-trained on Japanese Wikipedia and the Japanese portion of CC-100.", - "url": "https://huggingface.co/ku-nlp/roberta-large-japanese-char-wwm", - "project_name": "roberta-large-japanese-char-wwm", + "description": "japanese-gpt2-medium-unidic This is a medium-sized Japanese GPT-2 model using BERT-like tokenizer.", + "url": "https://huggingface.co/okazaki-lab/japanese-gpt2-medium-unidic", + "project_name": "japanese-gpt2-medium-unidic", "downloads": 14, "source": "Hugging Face", - "score": -0.11422593848148072, - "first_commit": "2022-09-18 08:10:44", - "latest_commit": "2023-03-19 01:58:12", + "score": -0.09264653326874964, + "first_commit": "2023-02-27 05:42:22", + "latest_commit": "2023-03-22 06:22:32", "languages": [], "model_or_dataset": "model", - "model_size": 0.323, - "model_architectures": "RobertaForMaskedLM" + "model_size": 0.362, + "model_architectures": "GPT2LMHeadModel" }, { - "description": "deberta-large-japanese-wikipedia Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-wikipedia", - "project_name": "deberta-large-japanese-wikipedia", + "description": "bart-base-japanese This model is converted from the original Japanese BART Pretrained model released by Kyoto University.", + "url": "https://huggingface.co/Formzu/bart-base-japanese", + "project_name": "bart-base-japanese", "downloads": 14, "source": "Hugging Face", - "score": -0.11422593848148072, - "first_commit": "2022-07-05 22:01:16", - "latest_commit": "2023-02-27 10:15:35", + "score": -0.09264653326874964, + "first_commit": "2022-10-31 06:52:38", + "latest_commit": "2022-11-07 11:13:39", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForMaskedLM" + "model_architectures": "MBartForConditionalGeneration" }, { - "description": "Google's mt5-base fine-tuned in Japanese to summarize patent claims in a limited Pharmaceutical domain. ", - "url": "https://huggingface.co/kz/mt5base-finetuned-patentsum-japanese-small", - "project_name": "mt5base-finetuned-patentsum-japanese-small", + "description": "japanese-soseki-gpt2-1b", + "url": "https://huggingface.co/jweb/japanese-soseki-gpt2-1b", + "project_name": "japanese-soseki-gpt2-1b", "downloads": 14, "source": "Hugging Face", - "score": -0.11422593848148072, - "first_commit": "2021-04-10 00:31:15", - "latest_commit": "2022-05-19 06:50:32", + "score": -0.09264653326874964, + "first_commit": "2022-03-03 04:53:15", + "latest_commit": "2023-03-27 12:09:04", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "MT5ForConditionalGeneration" + "model_architectures": "GPT2LMHeadModel" }, { "description": "roberta-large-japanese-aozora Model Description", @@ -12555,7 +13006,7 @@ "project_name": "roberta-large-japanese-aozora", "downloads": 14, "source": "Hugging Face", - "score": -0.11422593848148072, + "score": -0.09264653326874964, "first_commit": "2021-12-26 13:08:52", "latest_commit": "2022-10-15 14:22:11", "languages": [], @@ -12563,41 +13014,13 @@ "model_size": null, "model_architectures": "RobertaForMaskedLM" }, - { - "description": "Danbooru2023:", - "url": "https://huggingface.co/datasets/nyanko7/danbooru2023", - "project_name": "danbooru2023", - "downloads": 14, - "source": "Hugging Face", - "score": -0.11422593848148072, - "first_commit": "2024-01-07 19:51:58", - "latest_commit": "2024-05-22 18:43:24", - "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null - }, - { - "description": "固有表現ラベルはllm-book/ner-wikipedia-datasetと同様のものを採用しており、全部で8種類 (人名、法人名、地名、製品名、政治的組織名、施設名、その他の組織名、イベント名)あります。 ", - "url": "https://huggingface.co/datasets/llm-book/ner-wikinews-dataset", - "project_name": "ner-wikinews-dataset", - "downloads": 14, - "source": "Hugging Face", - "score": -0.11422593848148072, - "first_commit": "2023-04-22 14:32:21", - "latest_commit": "2023-12-12 11:22:26", - "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null - }, { "description": "GitHub リポジトリ singletongue/wikipedia-utils で公開されているデータセットを利用しています。 ", "url": "https://huggingface.co/datasets/llm-book/jawiki-paragraphs", "project_name": "jawiki-paragraphs", "downloads": 14, "source": "Hugging Face", - "score": -0.11422593848148072, + "score": -0.09264653326874964, "first_commit": "2023-06-03 03:04:05", "latest_commit": "2023-06-03 03:04:43", "languages": [], @@ -12606,60 +13029,60 @@ "model_architectures": null }, { - "description": "Amenokaku-Code-Instruct Update: 2023/12/27データセットに JaxTon , プロになるJava のコードデータ 180 レコードを追加しました。 ", - "url": "https://huggingface.co/datasets/kunishou/amenokaku-code-instruct", - "project_name": "amenokaku-code-instruct", - "downloads": 14, + "description": "bert-large-japanese-char-extended Model Description", + "url": "https://huggingface.co/KoichiYasuoka/bert-large-japanese-char-extended", + "project_name": "bert-large-japanese-char-extended", + "downloads": 13, "source": "Hugging Face", - "score": -0.11422593848148072, - "first_commit": "2023-10-01 01:04:50", - "latest_commit": "2024-04-01 17:01:54", + "score": -0.09265713821928598, + "first_commit": "2021-06-04 13:29:34", + "latest_commit": "2024-08-20 17:45:37", "languages": [], - "model_or_dataset": "dataset", + "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "BertForMaskedLM" }, { - "description": "bert-base-japanese-luw-upos Model Description", - "url": "https://huggingface.co/KoichiYasuoka/bert-base-japanese-luw-upos", - "project_name": "bert-base-japanese-luw-upos", + "description": "Unihan LM: Coarse-to-Fine Chinese-Japanese Language Model Pretraining with the Unihan Database Model description Chinese and Japanese share many characters with similar surface morphology.", + "url": "https://huggingface.co/microsoft/unihanlm-base", + "project_name": "unihanlm-base", "downloads": 13, "source": "Hugging Face", - "score": -0.11424164983817493, - "first_commit": "2021-10-26 13:26:38", - "latest_commit": "2022-09-18 19:43:18", + "score": -0.09265713821928598, + "first_commit": "2020-09-27 11:23:02", + "latest_commit": "2021-09-22 11:00:56", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "BertForTokenClassification" + "model_architectures": "XLMModel" }, { - "description": "ELECTRA small Japanese generator This is a ELECTRA model pretrained on texts in the Japanese language.", - "url": "https://huggingface.co/izumi-lab/electra-small-japanese-generator", - "project_name": "electra-small-japanese-generator", + "description": "wav2vec2-live-japanese https://github.com/ttop32/wav2vec2-live-japanese-translatorFine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese hiragana using the common_voice JSUT CSS10", + "url": "https://huggingface.co/ttop324/wav2vec2-live-japanese", + "project_name": "wav2vec2-live-japanese", "downloads": 13, "source": "Hugging Face", - "score": -0.11424164983817493, - "first_commit": "2021-10-04 13:43:37", - "latest_commit": "2023-10-21 13:21:28", + "score": -0.09265713821928598, + "first_commit": "2021-10-26 14:51:21", + "latest_commit": "2021-10-31 15:34:55", "languages": [], "model_or_dataset": "model", - "model_size": 0.013800000000000002, - "model_architectures": "ElectraForMaskedLM" + "model_size": null, + "model_architectures": "Wav2Vec2ForCTC" }, { - "description": "deberta-large-japanese-unidic Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-unidic", - "project_name": "deberta-large-japanese-unidic", + "description": "nlp-waseda/roberta-large-japanese-with-auto-jumanpp Model description", + "url": "https://huggingface.co/nlp-waseda/roberta-large-japanese-with-auto-jumanpp", + "project_name": "roberta-large-japanese-with-auto-jumanpp", "downloads": 13, "source": "Hugging Face", - "score": -0.11424164983817493, - "first_commit": "2022-06-10 12:49:12", - "latest_commit": "2022-06-19 09:15:35", + "score": -0.09265713821928598, + "first_commit": "2022-10-15 05:40:40", + "latest_commit": "2022-10-21 15:55:27", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForMaskedLM" + "model_architectures": "RobertaForMaskedLM" }, { "description": "Model Card for Model ID", @@ -12667,7 +13090,7 @@ "project_name": "mt5-mini9L", "downloads": 13, "source": "Hugging Face", - "score": -0.11424164983817493, + "score": -0.09265713821928598, "first_commit": "2023-03-30 01:11:17", "latest_commit": "2023-10-15 10:56:23", "languages": [], @@ -12676,96 +13099,40 @@ "model_architectures": "MT5ForConditionalGeneration" }, { - "description": "このモデルはdeberta-v2-large-japaneseをファインチューニングして固有表現抽出（NER）に用いれるようにしたものです。 ", - "url": "https://huggingface.co/Mizuiro-sakura/deberta-v2-large-japanese-finetuned-ner", - "project_name": "deberta-v2-large-japanese-finetuned-ner", - "downloads": 13, - "source": "Hugging Face", - "score": -0.11424164983817493, - "first_commit": "2023-05-10 13:22:23", - "latest_commit": "2023-07-21 14:10:02", - "languages": [], - "model_or_dataset": "model", - "model_size": 0.339, - "model_architectures": "DebertaV2ForTokenClassification" - }, - { - "description": "TaCOMET_ja", - "url": "https://huggingface.co/nlp-waseda/tacomet-gpt2-xl-japanese", - "project_name": "tacomet-gpt2-xl-japanese", - "downloads": 13, - "source": "Hugging Face", - "score": -0.11424164983817493, - "first_commit": "2024-03-07 11:50:15", - "latest_commit": "2024-06-05 09:41:05", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "GPT2LMHeadModel" - }, - { - "description": "SambaLingo-Japanese-Chat SambaLingo-Japanese-Chat is a human aligned chat model trained in Japanese and English.", - "url": "https://huggingface.co/LoneStriker/SambaLingo-Japanese-Chat-4.0bpw-h6-exl2", - "project_name": "SambaLingo-Japanese-Chat-4.0bpw-h6-exl2", + "description": "Chat & support: TheBloke's Discord server Want to contribute?", + "url": "https://huggingface.co/TheBloke/japanese-stablelm-base-beta-70B-GPTQ", + "project_name": "japanese-stablelm-base-beta-70B-GPTQ", "downloads": 13, "source": "Hugging Face", - "score": -0.11424164983817493, - "first_commit": "2024-03-07 06:51:43", - "latest_commit": "2024-03-07 06:53:26", + "score": -0.09265713821928598, + "first_commit": "2023-11-06 11:33:47", + "latest_commit": "2023-11-06 16:00:08", "languages": [], "model_or_dataset": "model", - "model_size": null, + "model_size": 9.1, "model_architectures": "LlamaForCausalLM" }, { - "description": "Our Models Vecteus Ninja-v1 Ninja-v1-NSFW Ninja-v1-128k Ninja-v1-NSFW-128k Model Card for Ninja-v1.0 The Mistral-7B--based Large Language Model (LLM) is an noveldataset fine-tuned version of the Mistral-7B-v0.1 Ninja has the following changes compared to Mistral-7B-v0.1.", - "url": "https://huggingface.co/Local-Novel-LLM-project/Ninja-v1", - "project_name": "Ninja-v1", + "description": "Shisa 7B Shisa 7B (shisa-7b-v1)", + "url": "https://huggingface.co/LoneStriker/shisa-7b-v1-5.0bpw-h6-exl2", + "project_name": "shisa-7b-v1-5.0bpw-h6-exl2", "downloads": 13, "source": "Hugging Face", - "score": -0.11424164983817493, - "first_commit": "2024-04-24 10:28:30", - "latest_commit": "2024-05-04 04:07:09", + "score": -0.09265713821928598, + "first_commit": "2023-12-07 18:07:21", + "latest_commit": "2023-12-07 18:54:27", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, + "model_size": null, "model_architectures": "MistralForCausalLM" }, - { - "description": "Assistance のGGUF版 Our Models for GGUF Vecteus-GGUF Ninja-v1-GGUF Ninja-v1-NSFW-GGUF Ninja-v1-128k-GGUF Ninja-v1-NSFW-128k-GGUF", - "url": "https://huggingface.co/Local-Novel-LLM-project/Assistance-GGUF", - "project_name": "Assistance-GGUF", - "downloads": 13, - "source": "Hugging Face", - "score": -0.11424164983817493, - "first_commit": "2024-05-03 04:03:47", - "latest_commit": "2024-05-03 04:30:45", - "languages": [], - "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": null - }, - { - "description": "Overview This model is based on rinna's [rinna/llama-3-youko-8b], fine-tuned using LoRA on a small number of parallel sentences from English to Japanese.", - "url": "https://huggingface.co/lyu-boxuan/llama-3-youko-8b-En-Ja-MT-LoRA", - "project_name": "llama-3-youko-8b-En-Ja-MT-LoRA", - "downloads": 13, - "source": "Hugging Face", - "score": -0.11424164983817493, - "first_commit": "2024-05-10 14:33:57", - "latest_commit": "2024-05-21 14:54:46", - "languages": [], - "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": "LlamaForCausalLM" - }, { "description": "Model Card for Model ID Fine tunned ASR model from distil-whisper/distil-large-v2.", "url": "https://huggingface.co/spow12/Visual-novel-transcriptor", "project_name": "Visual-novel-transcriptor", "downloads": 13, "source": "Hugging Face", - "score": -0.11424164983817493, + "score": -0.09265713821928598, "first_commit": "2024-04-15 01:43:08", "latest_commit": "2024-08-12 12:39:52", "languages": [], @@ -12774,452 +13141,354 @@ "model_architectures": "WhisperForConditionalGeneration" }, { - "description": "The English document is here モデル概要 Watashiha-Llama-2-13B-Ogiri-sftをAWSのinf2インスタンスで動作するようにコンパイルされたモデルです。 ", - "url": "https://huggingface.co/watashiha/Watashiha-Llama-2-13B-Ogiri-sft-neuron", - "project_name": "Watashiha-Llama-2-13B-Ogiri-sft-neuron", - "downloads": 13, - "source": "Hugging Face", - "score": -0.11424164983817493, - "first_commit": "2024-01-24 19:05:34", - "latest_commit": "2024-02-02 06:39:21", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "LlamaForCausalLM" - }, - { - "description": "Shisa 7B Shisa 7B (shisa-7b-v1)", - "url": "https://huggingface.co/LoneStriker/shisa-7b-v1-8.0bpw-h8-exl2", - "project_name": "shisa-7b-v1-8.0bpw-h8-exl2", - "downloads": 13, - "source": "Hugging Face", - "score": -0.11424164983817493, - "first_commit": "2023-12-07 18:22:23", - "latest_commit": "2023-12-07 18:54:33", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "MistralForCausalLM" - }, - { - "description": "deberta-base-japanese-wikipedia Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-wikipedia", - "project_name": "deberta-base-japanese-wikipedia", - "downloads": 13, - "source": "Hugging Face", - "score": -0.11424164983817493, - "first_commit": "2022-06-25 03:46:58", - "latest_commit": "2023-01-27 17:51:51", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "DebertaV2ForMaskedLM" - }, - { - "description": "deberta-small-japanese-upos Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-small-japanese-upos", - "project_name": "deberta-small-japanese-upos", + "description": "gpt2-medium-japanese-ud-causal Model Description", + "url": "https://huggingface.co/KoichiYasuoka/gpt2-medium-japanese-ud-causal", + "project_name": "gpt2-medium-japanese-ud-causal", "downloads": 13, "source": "Hugging Face", - "score": -0.11424164983817493, - "first_commit": "2022-05-23 23:55:56", - "latest_commit": "2024-07-26 15:38:41", + "score": -0.09265713821928598, + "first_commit": "2024-08-22 23:01:26", + "latest_commit": "2024-08-25 17:55:41", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForTokenClassification" + "model_architectures": "GPT2ForTokenClassification" }, { - "description": "roberta-small-japanese-aozora Model Description", - "url": "https://huggingface.co/KoichiYasuoka/roberta-small-japanese-aozora", - "project_name": "roberta-small-japanese-aozora", + "description": "gpt2-large-japanese-upos Model Description", + "url": "https://huggingface.co/KoichiYasuoka/gpt2-large-japanese-upos", + "project_name": "gpt2-large-japanese-upos", "downloads": 13, "source": "Hugging Face", - "score": -0.11424164983817493, - "first_commit": "2021-11-02 12:54:50", - "latest_commit": "2021-11-03 23:44:50", + "score": -0.09265713821928598, + "first_commit": "2024-06-22 22:44:06", + "latest_commit": "2024-07-27 07:49:47", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "RobertaForMaskedLM" + "model_architectures": "GPT2ForTokenClassification" }, { - "description": "mlx-community/Llama-3.1-70B-Japanese-Instruct-2407-8bit The Model mlx-community/Llama-3.1-70B-Japanese-Instruct-2407-8bit was converted to MLX format from cyberagent/Llama-3.1-70B-Japanese-Instruct-2407 using mlx-lm version 0.16.1.", - "url": "https://huggingface.co/mlx-community/Llama-3.1-70B-Japanese-Instruct-2407-8bit", - "project_name": "Llama-3.1-70B-Japanese-Instruct-2407-8bit", + "description": "Assistance のGGUF版 Our Models for GGUF Vecteus-GGUF Ninja-v1-GGUF Ninja-v1-NSFW-GGUF Ninja-v1-128k-GGUF Ninja-v1-NSFW-128k-GGUF", + "url": "https://huggingface.co/Local-Novel-LLM-project/Assistance-GGUF", + "project_name": "Assistance-GGUF", "downloads": 13, "source": "Hugging Face", - "score": -0.11424164983817493, - "first_commit": "2024-07-26 13:05:01", - "latest_commit": "2024-07-26 14:05:31", + "score": -0.09265713821928598, + "first_commit": "2024-05-03 04:03:47", + "latest_commit": "2024-05-03 04:30:45", "languages": [], "model_or_dataset": "model", - "model_size": 19.8, - "model_architectures": "LlamaForCausalLM" - }, - { - "description": "読み込み方 from datasets import load_dataset dataset = load_dataset(\"YANS-official/ogiri-bokete\", split=\"train\") 概要 大喜利投稿サイトBoketeのクロールデータです。", - "url": "https://huggingface.co/datasets/YANS-official/ogiri-bokete", - "project_name": "ogiri-bokete", - "downloads": 13, - "source": "Hugging Face", - "score": -0.11424164983817493, - "first_commit": "2024-07-21 09:58:15", - "latest_commit": "2024-08-31 09:24:55", - "languages": [], - "model_or_dataset": "dataset", - "model_size": null, + "model_size": 7.24, "model_architectures": null }, { - "description": "bert-large-japanese-unidic-luw-upos Model Description", - "url": "https://huggingface.co/KoichiYasuoka/bert-large-japanese-unidic-luw-upos", - "project_name": "bert-large-japanese-unidic-luw-upos", - "downloads": 12, - "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2022-02-13 01:00:41", - "latest_commit": "2023-11-05 18:44:20", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "BertForTokenClassification" - }, - { - "description": "Unihan LM: Coarse-to-Fine Chinese-Japanese Language Model Pretraining with the Unihan Database Model description Chinese and Japanese share many characters with similar surface morphology.", - "url": "https://huggingface.co/microsoft/unihanlm-base", - "project_name": "unihanlm-base", - "downloads": 12, - "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2020-09-27 11:23:02", - "latest_commit": "2021-09-22 11:00:56", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "XLMModel" - }, - { - "description": "Model Card for Model ID このモデルはrinna/japanese-gpt-1bをベースモデルとして、 コンテキストからの抽出型QAと、解答を新たなコンテキストでリファインするための学習を行ったモデルです。 ", - "url": "https://huggingface.co/oshizo/qa-refine-japanese-gpt-1b", - "project_name": "qa-refine-japanese-gpt-1b", - "downloads": 12, - "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2023-01-18 15:43:39", - "latest_commit": "2023-01-19 10:14:36", - "languages": [], - "model_or_dataset": "model", - "model_size": null, - "model_architectures": "GPT2LMHeadModel" - }, - { - "description": "Model card for model ID", - "url": "https://huggingface.co/retrieva-jp/t5-large-medium", - "project_name": "t5-large-medium", - "downloads": 12, + "description": "DavidAU/alpaca-guanaco-japanese-gpt-1b-Q8_0-GGUF", + "url": "https://huggingface.co/DavidAU/alpaca-guanaco-japanese-gpt-1b-Q8_0-GGUF", + "project_name": "alpaca-guanaco-japanese-gpt-1b-Q8_0-GGUF", + "downloads": 13, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2023-04-26 08:31:45", - "latest_commit": "2023-05-10 10:00:45", + "score": -0.09265713821928598, + "first_commit": "2024-04-20 08:49:14", + "latest_commit": "2024-04-20 08:49:19", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "T5ForConditionalGeneration" + "model_size": 1.39, + "model_architectures": null }, { - "description": "Aerner LM-v1 事前学習から全部日本語で学習させたモデルです。 ", - "url": "https://huggingface.co/aerner/lm-v1", - "project_name": "lm-v1", - "downloads": 12, + "description": "deberta-base-japanese-wikipedia-luw-upos Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-wikipedia-luw-upos", + "project_name": "deberta-base-japanese-wikipedia-luw-upos", + "downloads": 13, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2023-05-25 12:35:32", - "latest_commit": "2023-05-25 13:35:34", + "score": -0.09265713821928598, + "first_commit": "2022-06-25 06:28:11", + "latest_commit": "2024-08-20 17:53:34", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "LlamaForCausalLM" + "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "モデルの概略 東方Projectのキャラクターである霧雨魔理沙とおしゃべりできるモデルです。 ", - "url": "https://huggingface.co/tsukemono/japanese-novel-gpt-j-6b-f16-marisa", - "project_name": "japanese-novel-gpt-j-6b-f16-marisa", - "downloads": 12, + "description": "日本語T5事前学習済みモデル This is a T5 (Text-to-Text Transfer Transformer) model pretrained on Japanese corpus. ", + "url": "https://huggingface.co/sonoisa/t5-base-japanese-mC4-Wikipedia", + "project_name": "t5-base-japanese-mC4-Wikipedia", + "downloads": 13, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2023-09-02 15:15:51", - "latest_commit": "2023-09-06 18:42:50", + "score": -0.09265713821928598, + "first_commit": "2021-06-30 12:53:09", + "latest_commit": "2021-09-23 18:29:58", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "GPTJForCausalLM" + "model_architectures": null }, { - "description": "Japanese Stable LM Instruct Gamma 7B Model Description", - "url": "https://huggingface.co/LoneStriker/stabilityai_japanese-stablelm-instruct-gamma-7b-8.0bpw-h6-exl2", - "project_name": "stabilityai_japanese-stablelm-instruct-gamma-7b-8.0bpw-h6-exl2", + "description": "RakutenAI-7B-upos Model Description", + "url": "https://huggingface.co/KoichiYasuoka/RakutenAI-7B-upos", + "project_name": "RakutenAI-7B-upos", "downloads": 12, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2023-10-28 20:43:59", - "latest_commit": "2023-10-28 15:44:20", + "score": -0.0926677431698223, + "first_commit": "2024-07-11 06:42:57", + "latest_commit": "2024-08-20 17:20:57", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "MistralForCausalLM" + "model_architectures": "MistralForTokenClassification" }, { - "description": "Japanese Stable LM Instruct Gamma 7B Model Description", - "url": "https://huggingface.co/LoneStriker/stabilityai_japanese-stablelm-instruct-gamma-7b-5.0bpw-h6-exl2", - "project_name": "stabilityai_japanese-stablelm-instruct-gamma-7b-5.0bpw-h6-exl2", + "description": "This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - JA dataset.", + "url": "https://huggingface.co/AndrewMcDowell/wav2vec2-xls-r-1b-japanese-hiragana-katakana", + "project_name": "wav2vec2-xls-r-1b-japanese-hiragana-katakana", "downloads": 12, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2023-10-28 20:29:59", - "latest_commit": "2023-10-28 15:30:13", + "score": -0.0926677431698223, + "first_commit": "2022-02-04 11:27:09", + "latest_commit": "2022-03-24 11:56:32", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "MistralForCausalLM" + "model_architectures": "Wav2Vec2ForCTC" }, { - "description": "SambaLingo-Japanese-Chat SambaLingo-Japanese-Chat is a human aligned chat model trained in Japanese and English.", - "url": "https://huggingface.co/LoneStriker/SambaLingo-Japanese-Chat-6.0bpw-h6-exl2", - "project_name": "SambaLingo-Japanese-Chat-6.0bpw-h6-exl2", + "description": "Example ESPnet2 TTS model kan-bayashi/jsut_transformer_accent_with_pause ♻", + "url": "https://huggingface.co/espnet/kan-bayashi_jsut_transformer_accent_with_pause", + "project_name": "kan-bayashi_jsut_transformer_accent_with_pause", "downloads": 12, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2024-03-07 06:55:28", - "latest_commit": "2024-03-07 06:57:49", + "score": -0.0926677431698223, + "first_commit": "2021-07-03 14:53:36", + "latest_commit": "2021-07-03 11:04:24", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "LlamaForCausalLM" + "model_architectures": null }, { - "description": "Introduction Who am I: Qishen Ha", - "url": "https://huggingface.co/haqishen/h2o-Llama-3-8B-Japanese-Instruct", - "project_name": "h2o-Llama-3-8B-Japanese-Instruct", + "description": "ELECTRA small Japanese discriminator This is a ELECTRA model pretrained on texts in the Japanese language.", + "url": "https://huggingface.co/izumi-lab/electra-small-japanese-discriminator", + "project_name": "electra-small-japanese-discriminator", "downloads": 12, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2024-04-24 07:48:45", - "latest_commit": "2024-06-24 08:57:49", + "score": -0.0926677431698223, + "first_commit": "2021-10-04 13:42:57", + "latest_commit": "2022-12-09 00:41:39", "languages": [], "model_or_dataset": "model", - "model_size": 8.03, - "model_architectures": "LlamaForCausalLM" + "model_size": null, + "model_architectures": "ElectraForPreTraining" }, { - "description": "This repository contains a model trained (QLoRA-SFT)", - "url": "https://huggingface.co/taoki/phi3-mini-4k-qlora-jmultiwoz-dolly-amenokaku-alpaca_jp_python-GGUF", - "project_name": "phi3-mini-4k-qlora-jmultiwoz-dolly-amenokaku-alpaca_jp_python-GGUF", + "description": "nlp-waseda/gpt2-small-japanese-wikipedia This model is Japanese GPT-2 pretrained on Japanese Wikipedia.", + "url": "https://huggingface.co/nlp-waseda/gpt2-small-japanese-wikipedia", + "project_name": "gpt2-small-japanese-wikipedia", "downloads": 12, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2024-05-29 15:11:10", - "latest_commit": "2024-05-31 11:28:45", + "score": -0.0926677431698223, + "first_commit": "2021-12-28 01:22:40", + "latest_commit": "2021-12-28 15:31:38", "languages": [], "model_or_dataset": "model", - "model_size": 3.82, - "model_architectures": null + "model_size": null, + "model_architectures": "GPT2LMHeadModel" }, { - "description": "youhansun/Llama-3-70B-japanese-suzume-vector-v0.1-Q2_K-GGUF", - "url": "https://huggingface.co/youhansun/Llama-3-70B-japanese-suzume-vector-v0.1-Q2_K-GGUF", - "project_name": "Llama-3-70B-japanese-suzume-vector-v0.1-Q2_K-GGUF", + "description": "このモデルはdeberta-v2-tiny-japaneseをファインチューニングしてQAタスクに用いれるようにしたものです。 ", + "url": "https://huggingface.co/Mizuiro-sakura/deberta-v2-tiny-japanese-finetuned-QA", + "project_name": "deberta-v2-tiny-japanese-finetuned-QA", "downloads": 12, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2024-06-02 04:49:31", - "latest_commit": "2024-06-02 04:52:45", + "score": -0.0926677431698223, + "first_commit": "2023-05-11 10:34:38", + "latest_commit": "2023-05-11 10:38:32", "languages": [], "model_or_dataset": "model", - "model_size": 70.6, - "model_architectures": null + "model_size": null, + "model_architectures": "DebertaV2ForQuestionAnswering" }, { - "description": "gpt2-medium-japanese-ud-causal Model Description", - "url": "https://huggingface.co/KoichiYasuoka/gpt2-medium-japanese-ud-causal", - "project_name": "gpt2-medium-japanese-ud-causal", + "description": "Shisa 7B Shisa 7B (shisa-7b-v1)", + "url": "https://huggingface.co/LoneStriker/shisa-7b-v1-8.0bpw-h8-exl2", + "project_name": "shisa-7b-v1-8.0bpw-h8-exl2", "downloads": 12, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2024-08-22 23:01:26", - "latest_commit": "2024-08-25 17:55:41", + "score": -0.0926677431698223, + "first_commit": "2023-12-07 18:22:23", + "latest_commit": "2023-12-07 18:54:33", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "GPT2ForTokenClassification" + "model_architectures": "MistralForCausalLM" }, { - "description": "ChatGLM3-6B是一个中英双语大模型，本项目为ChatGLM3-6B加入日文能力。", - "url": "https://huggingface.co/dummy-foo/ChatGLM3-Japanese", - "project_name": "ChatGLM3-Japanese", + "description": "Overview This model is based on rinna's [rinna/llama-3-youko-8b], fine-tuned using LoRA on a small number of parallel sentences from English to Japanese.", + "url": "https://huggingface.co/lyu-boxuan/llama-3-youko-8b-En-Ja-MT-LoRA", + "project_name": "llama-3-youko-8b-En-Ja-MT-LoRA", "downloads": 12, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2024-05-31 22:51:11", - "latest_commit": "2024-06-09 15:37:04", + "score": -0.0926677431698223, + "first_commit": "2024-05-10 14:33:57", + "latest_commit": "2024-05-21 14:54:46", "languages": [], "model_or_dataset": "model", - "model_size": 6.35, - "model_architectures": "ChatGLMForConditionalGeneration" + "model_size": 8.03, + "model_architectures": "LlamaForCausalLM" }, { - "description": "Ninja-v1-RP-WIP 概要 Local-Novel-LLM-project/Ninja-v1-NSFWをロールプレイ用にLoRAでファインチューニングしたモデルです。 ", - "url": "https://huggingface.co/Aratako/Ninja-v1-RP-WIP", - "project_name": "Ninja-v1-RP-WIP", + "description": "ELYZA-japanese-Llama-2-MoE-2x13B-v0.1-GGUF 概要 Aratako/ELYZA-japanese-Llama-2-MoE-2x13B-v0.1の量子化済みGGUF版です。", + "url": "https://huggingface.co/Aratako/ELYZA-japanese-Llama-2-MoE-2x13B-v0.1-GGUF", + "project_name": "ELYZA-japanese-Llama-2-MoE-2x13B-v0.1-GGUF", "downloads": 12, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2024-05-19 15:31:02", - "latest_commit": "2024-05-20 16:56:00", + "score": -0.0926677431698223, + "first_commit": "2024-03-03 12:51:40", + "latest_commit": "2024-03-03 13:39:01", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": "MistralForCausalLM" + "model_size": 21.5, + "model_architectures": null }, { - "description": "モデル概要 Watashiha-Llama-2-13B-Ogiri-sftをLLaVAで学習し、画像に対応した大喜利言語モデルです。", - "url": "https://huggingface.co/watashiha/Watashiha-Llama-2-13B-Ogiri-sft-vlm", - "project_name": "Watashiha-Llama-2-13B-Ogiri-sft-vlm", + "description": "COMET-GPT2 ja v2 Finetuned GPT-2 xl on the large version of ATOMIC ja using a causal language modeling (CLM) objective.", + "url": "https://huggingface.co/nlp-waseda/comet-gpt2-xl-japanese", + "project_name": "comet-gpt2-xl-japanese", "downloads": 12, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2024-02-26 17:55:56", - "latest_commit": "2024-03-04 05:22:43", + "score": -0.0926677431698223, + "first_commit": "2023-09-26 13:37:52", + "latest_commit": "2024-03-11 04:16:02", "languages": [], "model_or_dataset": "model", - "model_size": 13.3, - "model_architectures": "LlavaLlamaForCausalLM" + "model_size": null, + "model_architectures": "GPT2LMHeadModel" }, { - "description": "Orion-14B 🌐English | 🇨", - "url": "https://huggingface.co/zaq-hack/Orion-14B-LongChat-bpw600-h6-exl2", - "project_name": "Orion-14B-LongChat-bpw600-h6-exl2", + "description": "Model Card for Japanese DeBERTa V2 base Model description This is a Japanese DeBERTa V2 base model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.", + "url": "https://huggingface.co/G-Root/deberta-v2-base-japanese", + "project_name": "deberta-v2-base-japanese", "downloads": 12, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2024-01-25 16:58:27", - "latest_commit": "2024-01-25 21:01:29", + "score": -0.0926677431698223, + "first_commit": "2023-09-14 10:06:00", + "latest_commit": "2023-09-14 17:24:52", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "OrionForCausalLM" + "model_size": 0.137, + "model_architectures": "DebertaV2ForMaskedLM" }, { - "description": "This model was created by merging intfloat/e5-mistral-7b-instruct and stabilityai/japanese-stablelm-base-gamma-7b.", - "url": "https://huggingface.co/oshizo/japanese-e5-mistral-7b_slerp", - "project_name": "japanese-e5-mistral-7b_slerp", + "description": "このモデルはdeberta-v2-large-japaneseをファインチューニングして固有表現抽出（NER）に用いれるようにしたものです。 ", + "url": "https://huggingface.co/Mizuiro-sakura/deberta-v2-large-japanese-finetuned-ner", + "project_name": "deberta-v2-large-japanese-finetuned-ner", "downloads": 12, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2024-01-04 12:33:19", - "latest_commit": "2024-01-05 15:48:24", + "score": -0.0926677431698223, + "first_commit": "2023-05-10 13:22:23", + "latest_commit": "2023-07-21 14:10:02", "languages": [], "model_or_dataset": "model", - "model_size": 7.24, - "model_architectures": "MistralModel" + "model_size": 0.339, + "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "Shisa 7B Shisa 7B (shisa-7b-v1)", - "url": "https://huggingface.co/LoneStriker/shisa-7b-v1-4.0bpw-h6-exl2", - "project_name": "shisa-7b-v1-4.0bpw-h6-exl2", + "description": "deberta-small-japanese-luw-upos Model Description", + "url": "https://huggingface.co/KoichiYasuoka/deberta-small-japanese-luw-upos", + "project_name": "deberta-small-japanese-luw-upos", "downloads": 12, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2023-12-07 17:59:51", - "latest_commit": "2023-12-07 18:54:26", + "score": -0.0926677431698223, + "first_commit": "2022-05-24 03:52:45", + "latest_commit": "2024-08-20 17:28:44", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "MistralForCausalLM" + "model_architectures": "DebertaV2ForTokenClassification" }, { - "description": "Chat & support: TheBloke's Discord server Want to contribute?", - "url": "https://huggingface.co/TheBloke/japanese-stablelm-base-beta-70B-GPTQ", - "project_name": "japanese-stablelm-base-beta-70B-GPTQ", + "description": "roberta-small-japanese-aozora Model Description", + "url": "https://huggingface.co/KoichiYasuoka/roberta-small-japanese-aozora", + "project_name": "roberta-small-japanese-aozora", "downloads": 12, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2023-11-06 11:33:47", - "latest_commit": "2023-11-06 16:00:08", + "score": -0.0926677431698223, + "first_commit": "2021-11-02 12:54:50", + "latest_commit": "2021-11-03 23:44:50", "languages": [], "model_or_dataset": "model", - "model_size": 9.1, - "model_architectures": "LlamaForCausalLM" + "model_size": null, + "model_architectures": "RobertaForMaskedLM" }, { - "description": "(English part follows Japanese one.", - "url": "https://huggingface.co/tohoku-nlp/stable-diffusion-xl-jp-base-1.0", - "project_name": "stable-diffusion-xl-jp-base-1.0", + "description": "Amenokaku-Code-Instruct Update: 2023/12/27データセットに JaxTon , プロになるJava のコードデータ 180 レコードを追加しました。 ", + "url": "https://huggingface.co/datasets/kunishou/amenokaku-code-instruct", + "project_name": "amenokaku-code-instruct", "downloads": 12, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2023-11-06 05:02:27", - "latest_commit": "2023-11-06 05:37:01", + "score": -0.0926677431698223, + "first_commit": "2023-10-01 01:04:50", + "latest_commit": "2024-04-01 17:01:54", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "deberta-base-japanese-wikipedia-ud-goeswith Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-base-japanese-wikipedia-ud-goeswith", - "project_name": "deberta-base-japanese-wikipedia-ud-goeswith", + "description": "Introduction This is a LLM-filtered set of the first 1M rows from ntt's JParaCrawl v3 large English-Japanese parallel corpus.", + "url": "https://huggingface.co/datasets/Verah/JParaCrawl-Filtered-English-Japanese-Parallel-Corpus", + "project_name": "JParaCrawl-Filtered-English-Japanese-Parallel-Corpus", "downloads": 12, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2022-09-18 06:02:55", - "latest_commit": "2024-08-20 19:38:50", + "score": -0.0926677431698223, + "first_commit": "2024-03-01 06:17:09", + "latest_commit": "2024-03-07 21:20:21", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "DebertaV2ForTokenClassification" + "model_architectures": null }, { - "description": "roberta-large-japanese-char-luw-upos Model Description", - "url": "https://huggingface.co/KoichiYasuoka/roberta-large-japanese-char-luw-upos", - "project_name": "roberta-large-japanese-char-luw-upos", + "description": "Synthetic-JP-EN-Coding-Dataset-Magpie-69k Magpieの手法を様々なモデルに対して適用し作成した、約69000件の日本語・英語のコーディング対話データセットです。 ", + "url": "https://huggingface.co/datasets/Aratako/Synthetic-JP-EN-Coding-Dataset-Magpie-69k", + "project_name": "Synthetic-JP-EN-Coding-Dataset-Magpie-69k", "downloads": 12, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2021-12-30 15:56:46", - "latest_commit": "2022-09-18 19:44:49", + "score": -0.0926677431698223, + "first_commit": "2024-07-11 10:19:45", + "latest_commit": "2024-07-11 12:07:01", "languages": [], - "model_or_dataset": "model", + "model_or_dataset": "dataset", "model_size": null, - "model_architectures": "RobertaForTokenClassification" + "model_architectures": null }, { - "description": "Synthetic-Japanese-Roleplay-gpt-4o-mini-19.8k-formatted 概要 gpt-4o-miniを用いて作成した日本語ロールプレイデータセットであるAratako/Synthetic-Japanese-Roleplay-gpt-4o-mini-19.8kにsystem messageを追加して整形したデータセットです。 ", - "url": "https://huggingface.co/datasets/Aratako/Synthetic-Japanese-Roleplay-gpt-4o-mini-19.8k-formatted", - "project_name": "Synthetic-Japanese-Roleplay-gpt-4o-mini-19.8k-formatted", + "description": "English - Japanese pairs taken from https://tatoeba.org/en/downloads and then deduplicated.", + "url": "https://huggingface.co/datasets/Verah/tatoeba_dedupe_en-jp_2024-March-01", + "project_name": "tatoeba_dedupe_en-jp_2024-March-01", "downloads": 12, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2024-08-16 16:46:06", - "latest_commit": "2024-08-16 16:54:03", + "score": -0.0926677431698223, + "first_commit": "2024-03-05 13:46:13", + "latest_commit": "2024-03-06 08:34:02", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "Dataset Summary JMultiWOZ is a large-scale Japanese multi-domain task-oriented dialogue dataset.", - "url": "https://huggingface.co/datasets/nu-dialogue/jmultiwoz", - "project_name": "jmultiwoz", - "downloads": 12, + "description": "mlx-community/Llama-3.1-70B-Japanese-Instruct-2407-8bit The Model mlx-community/Llama-3.1-70B-Japanese-Instruct-2407-8bit was converted to MLX format from cyberagent/Llama-3.1-70B-Japanese-Instruct-2407 using mlx-lm version 0.16.1.", + "url": "https://huggingface.co/mlx-community/Llama-3.1-70B-Japanese-Instruct-2407-8bit", + "project_name": "Llama-3.1-70B-Japanese-Instruct-2407-8bit", + "downloads": 11, "source": "Hugging Face", - "score": -0.11425736119486915, - "first_commit": "2024-02-29 15:38:29", - "latest_commit": "2024-03-13 02:15:37", + "score": -0.09267834812035865, + "first_commit": "2024-07-26 13:05:01", + "latest_commit": "2024-07-26 14:05:31", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null + "model_or_dataset": "model", + "model_size": 19.8, + "model_architectures": "LlamaForCausalLM" }, { "description": "bert-base-japanese-unidic-luw-upos Model Description", @@ -13227,7 +13496,7 @@ "project_name": "bert-base-japanese-unidic-luw-upos", "downloads": 11, "source": "Hugging Face", - "score": -0.11427307255156337, + "score": -0.09267834812035865, "first_commit": "2022-02-13 01:00:01", "latest_commit": "2023-11-05 18:44:10", "languages": [], @@ -13236,32 +13505,32 @@ "model_architectures": "BertForTokenClassification" }, { - "description": "Model Trained Using AutoNLP Problem type: Binary Classification Model ID: 59363 Validation Metrics Loss: 0.12651239335536957 Accuracy: 0.9532079853817648 Precision: 0.9729688278823665 Recall: 0.9744633462616643 AUC: 0.9717333684823413 F1: 0.9737155136027014 Usage You can use cURL to access this model: $ curl -X POST -H \"Authorization: Bearer YOUR_API_KEY\" -H \"Content-Type: application/json\" -d '{\"inputs\": \"I love AutoNLP\"}' https://api-inference.huggingface.co/models/abhishek/autonlp-japanese-sentiment-5936", - "url": "https://huggingface.co/abhishek/autonlp-japanese-sentiment-59363", - "project_name": "autonlp-japanese-sentiment-59363", + "description": "bert-base-japanese-luw-upos Model Description", + "url": "https://huggingface.co/KoichiYasuoka/bert-base-japanese-luw-upos", + "project_name": "bert-base-japanese-luw-upos", "downloads": 11, "source": "Hugging Face", - "score": -0.11427307255156337, - "first_commit": "2021-04-21 11:28:24", - "latest_commit": "2021-05-18 22:56:15", + "score": -0.09267834812035865, + "first_commit": "2021-10-26 13:26:38", + "latest_commit": "2022-09-18 19:43:18", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "BertForSequenceClassification" + "model_architectures": "BertForTokenClassification" }, { - "description": "yacis-electra-small", - "url": "https://huggingface.co/ptaszynski/yacis-electra-small-japanese", - "project_name": "yacis-electra-small-japanese", + "description": "transformers-ud-japanese-electra-ginza (sudachitra-wordpiece, mC4 Japanese)", + "url": "https://huggingface.co/megagonlabs/transformers-ud-japanese-electra-base-ginza", + "project_name": "transformers-ud-japanese-electra-base-ginza", "downloads": 11, "source": "Hugging Face", - "score": -0.11427307255156337, - "first_commit": "2022-01-12 01:48:13", - "latest_commit": "2022-01-13 01:43:17", + "score": -0.09267834812035865, + "first_commit": "2021-08-23 09:54:23", + "latest_commit": "2021-09-22 11:00:17", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": null + "model_architectures": "ElectraForPreTraining" }, { "description": "nlp-waseda/roberta-large-japanese-seq512-with-auto-jumanpp Model description", @@ -13269,7 +13538,7 @@ "project_name": "roberta-large-japanese-seq512-with-auto-jumanpp", "downloads": 11, "source": "Hugging Face", - "score": -0.11427307255156337, + "score": -0.09267834812035865, "first_commit": "2022-10-15 06:04:06", "latest_commit": "2022-10-21 15:56:38", "languages": [], @@ -13278,200 +13547,323 @@ "model_architectures": "RobertaForMaskedLM" }, { - "description": "deberta-large-japanese-juman-ud-goeswith Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-juman-ud-goeswith", - "project_name": "deberta-large-japanese-juman-ud-goeswith", + "description": "Aerner LM-v1 事前学習から全部日本語で学習させたモデルです。 ", + "url": "https://huggingface.co/aerner/lm-v1", + "project_name": "lm-v1", "downloads": 11, "source": "Hugging Face", - "score": -0.11427307255156337, - "first_commit": "2023-02-05 13:24:47", - "latest_commit": "2024-08-30 14:27:11", + "score": -0.09267834812035865, + "first_commit": "2023-05-25 12:35:32", + "latest_commit": "2023-05-25 13:35:34", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForTokenClassification" + "model_architectures": "LlamaForCausalLM" }, { - "description": "roberta-large-japanese-juman-ud-goeswith Model Description", - "url": "https://huggingface.co/KoichiYasuoka/roberta-large-japanese-juman-ud-goeswith", - "project_name": "roberta-large-japanese-juman-ud-goeswith", + "description": "whisper-large-v2-jp model for CTranslate2 This repository contains the conversion of vumichien/whisper-large-v2-jp to the CTranslate2 model format.", + "url": "https://huggingface.co/arc-r/faster-whisper-large-v2-jp", + "project_name": "faster-whisper-large-v2-jp", "downloads": 11, "source": "Hugging Face", - "score": -0.11427307255156337, - "first_commit": "2023-02-21 06:38:32", - "latest_commit": "2024-08-30 14:49:26", + "score": -0.09267834812035865, + "first_commit": "2023-07-07 06:16:06", + "latest_commit": "2023-07-07 18:09:09", + "languages": [], + "model_or_dataset": "model", + "model_size": null, + "model_architectures": null + }, + { + "description": "Shisa 7B Shisa 7B (shisa-7b-v1)", + "url": "https://huggingface.co/LoneStriker/shisa-7b-v1-6.0bpw-h6-exl2", + "project_name": "shisa-7b-v1-6.0bpw-h6-exl2", + "downloads": 11, + "source": "Hugging Face", + "score": -0.09267834812035865, + "first_commit": "2023-12-07 18:14:46", + "latest_commit": "2023-12-07 18:58:23", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "RobertaForTokenClassification" + "model_architectures": "MistralForCausalLM" }, { - "description": "Chat & support: TheBloke's Discord server Want to contribute?", - "url": "https://huggingface.co/TheBloke/japanese-stablelm-instruct-beta-7B-GPTQ", - "project_name": "japanese-stablelm-instruct-beta-7B-GPTQ", + "description": "Shisa 7B Shisa 7B (shisa-7b-v1)", + "url": "https://huggingface.co/LoneStriker/shisa-7b-v1-4.0bpw-h6-exl2", + "project_name": "shisa-7b-v1-4.0bpw-h6-exl2", "downloads": 11, "source": "Hugging Face", - "score": -0.11427307255156337, - "first_commit": "2023-11-03 10:31:29", - "latest_commit": "2023-11-03 12:54:41", + "score": -0.09267834812035865, + "first_commit": "2023-12-07 17:59:51", + "latest_commit": "2023-12-07 18:54:26", "languages": [], "model_or_dataset": "model", - "model_size": 1.13, - "model_architectures": "LlamaForCausalLM" + "model_size": null, + "model_architectures": "MistralForCausalLM" }, { - "description": "japanese-novel-gpt-j-6b https://huggingface.co/AIBunCho/japanese-novel-gpt-j-6b\" に合計216個の評価の高いなろう小説、青空文庫、ウィキペディアなどの文章をQLoRA学習させた小説生成用モデルです。 ", - "url": "https://huggingface.co/akineAItech/Jeneri-SAMA-6B", - "project_name": "Jeneri-SAMA-6B", + "description": "This repository contains a model trained (QLoRA-SFT)", + "url": "https://huggingface.co/taoki/phi3-mini-4k-qlora-jmultiwoz-dolly-amenokaku-alpaca_jp_python-GGUF", + "project_name": "phi3-mini-4k-qlora-jmultiwoz-dolly-amenokaku-alpaca_jp_python-GGUF", "downloads": 11, "source": "Hugging Face", - "score": -0.11427307255156337, - "first_commit": "2024-02-25 10:30:06", - "latest_commit": "2024-03-16 15:00:14", + "score": -0.09267834812035865, + "first_commit": "2024-05-29 15:11:10", + "latest_commit": "2024-05-31 11:28:45", "languages": [], "model_or_dataset": "model", - "model_size": 6.05, - "model_architectures": "GPTJForCausalLM" + "model_size": 3.82, + "model_architectures": null }, { - "description": "llm-jp-1.3b-v1.0-aya llm-jp's llm-jp-1.3b-v1.0 model fine-tuned on the Japanese examples from Cohere's aya dataset Model llm-jp-eval AVG kcoopermiller/llm-jp-1.3b-v1.0-aya 0.0698 llm-jp/llm-jp-1.3b-v1.0 0.047 How to use import torch from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained(\"kcoopermiller/llm-jp-1.3b-v1.0-aya\")", - "url": "https://huggingface.co/kcoopermiller/llm-jp-1.3b-v1.0-aya", - "project_name": "llm-jp-1.3b-v1.0-aya", + "description": "Llama-3-Umievo-itr014-Shizuko-8b このモデルは日本語に対応しているLlama-3ベースの４つのモデルを進化的アルゴリズムで進化的マージしたものです。", + "url": "https://huggingface.co/umiyuki/Llama-3-Umievo-itr014-Shizuko-8b", + "project_name": "Llama-3-Umievo-itr014-Shizuko-8b", "downloads": 11, "source": "Hugging Face", - "score": -0.11427307255156337, - "first_commit": "2024-02-23 05:39:39", - "latest_commit": "2024-02-29 23:48:58", + "score": -0.09267834812035865, + "first_commit": "2024-06-08 05:25:05", + "latest_commit": "2024-06-08 07:47:59", "languages": [], "model_or_dataset": "model", - "model_size": 1.32, - "model_architectures": "GPT2LMHeadModel" + "model_size": 8.03, + "model_architectures": "LlamaForCausalLM" }, { "description": "SambaLingo-Japanese-Chat SambaLingo-Japanese-Chat is a human aligned chat model trained in Japanese and English.", - "url": "https://huggingface.co/LoneStriker/SambaLingo-Japanese-Chat-8.0bpw-h8-exl2", - "project_name": "SambaLingo-Japanese-Chat-8.0bpw-h8-exl2", + "url": "https://huggingface.co/LoneStriker/SambaLingo-Japanese-Chat-3.0bpw-h6-exl2", + "project_name": "SambaLingo-Japanese-Chat-3.0bpw-h6-exl2", "downloads": 11, "source": "Hugging Face", - "score": -0.11427307255156337, - "first_commit": "2024-03-07 06:57:50", - "latest_commit": "2024-03-07 07:00:51", + "score": -0.09267834812035865, + "first_commit": "2024-03-07 06:50:19", + "latest_commit": "2024-03-07 06:51:42", "languages": [], "model_or_dataset": "model", "model_size": null, "model_architectures": "LlamaForCausalLM" }, { - "description": "ELYZA-japanese-Llama-2-MoE-2x7B-v0.1-GGUF 概要 Aratako/ELYZA-japanese-Llama-2-MoE-2x7B-v0.1の量子化済みGGUF版です。", - "url": "https://huggingface.co/Aratako/ELYZA-japanese-Llama-2-MoE-2x7B-v0.1-GGUF", - "project_name": "ELYZA-japanese-Llama-2-MoE-2x7B-v0.1-GGUF", - "downloads": 11, - "source": "Hugging Face", - "score": -0.11427307255156337, - "first_commit": "2024-03-06 15:44:10", - "latest_commit": "2024-03-07 13:23:01", - "languages": [], - "model_or_dataset": "model", - "model_size": 11.1, - "model_architectures": null - }, - { - "description": "ELYZA-japanese-Llama-2-MoE-2x7B-v0.1 English description here 概要 Llama-2ベースの学習済み日本語モデルであるelyza/ELYZA-japanese-Llama-2-7bと、そのinstruction tuningモデルであるelyza/ELYZA-japanese-Llama-2-7b-instruct を、mergekitを使ってMoEを行い作成したモデルです。 ", - "url": "https://huggingface.co/Aratako/ELYZA-japanese-Llama-2-MoE-2x7B-v0.1", - "project_name": "ELYZA-japanese-Llama-2-MoE-2x7B-v0.1", + "description": "Japanese Stable LM Instruct Gamma 7B Model Description", + "url": "https://huggingface.co/LoneStriker/stabilityai_japanese-stablelm-instruct-gamma-7b-8.0bpw-h6-exl2", + "project_name": "stabilityai_japanese-stablelm-instruct-gamma-7b-8.0bpw-h6-exl2", "downloads": 11, "source": "Hugging Face", - "score": -0.11427307255156337, - "first_commit": "2024-03-06 11:07:05", - "latest_commit": "2024-03-19 02:31:33", + "score": -0.09267834812035865, + "first_commit": "2023-10-28 20:43:59", + "latest_commit": "2023-10-28 15:44:20", "languages": [], "model_or_dataset": "model", - "model_size": 11.1, - "model_architectures": "MixtralForCausalLM" + "model_size": null, + "model_architectures": "MistralForCausalLM" }, { - "description": "Shisa 7B Shisa 7B (shisa-7b-v1)", - "url": "https://huggingface.co/LoneStriker/shisa-7b-v1-6.0bpw-h6-exl2", - "project_name": "shisa-7b-v1-6.0bpw-h6-exl2", + "description": "Japanese Stable LM Instruct Gamma 7B Model Description", + "url": "https://huggingface.co/LoneStriker/stabilityai_japanese-stablelm-instruct-gamma-7b-5.0bpw-h6-exl2", + "project_name": "stabilityai_japanese-stablelm-instruct-gamma-7b-5.0bpw-h6-exl2", "downloads": 11, "source": "Hugging Face", - "score": -0.11427307255156337, - "first_commit": "2023-12-07 18:14:46", - "latest_commit": "2023-12-07 18:58:23", + "score": -0.09267834812035865, + "first_commit": "2023-10-28 20:29:59", + "latest_commit": "2023-10-28 15:30:13", "languages": [], "model_or_dataset": "model", "model_size": null, "model_architectures": "MistralForCausalLM" }, { - "description": "Shisa 7B Shisa 7B (shisa-7b-v1)", - "url": "https://huggingface.co/LoneStriker/shisa-7b-v1-5.0bpw-h6-exl2", - "project_name": "shisa-7b-v1-5.0bpw-h6-exl2", + "description": "Chat & support: TheBloke's Discord server Want to contribute?", + "url": "https://huggingface.co/TheBloke/japanese-stablelm-instruct-gamma-7B-GPTQ", + "project_name": "japanese-stablelm-instruct-gamma-7B-GPTQ", "downloads": 11, "source": "Hugging Face", - "score": -0.11427307255156337, - "first_commit": "2023-12-07 18:07:21", - "latest_commit": "2023-12-07 18:54:27", + "score": -0.09267834812035865, + "first_commit": "2023-10-28 19:03:17", + "latest_commit": "2023-10-28 20:24:40", "languages": [], "model_or_dataset": "model", - "model_size": null, + "model_size": 1.2, "model_architectures": "MistralForCausalLM" }, { - "description": "deberta-large-japanese-wikipedia-ud-goeswith Model Description", - "url": "https://huggingface.co/KoichiYasuoka/deberta-large-japanese-wikipedia-ud-goeswith", - "project_name": "deberta-large-japanese-wikipedia-ud-goeswith", + "description": "Example ESPnet2 TTS model kan-bayashi/jsut_fastspeech ♻", + "url": "https://huggingface.co/espnet/kan-bayashi_jsut_fastspeech", + "project_name": "kan-bayashi_jsut_fastspeech", "downloads": 11, "source": "Hugging Face", - "score": -0.11427307255156337, - "first_commit": "2022-09-18 08:41:06", - "latest_commit": "2023-05-12 01:29:13", + "score": -0.09267834812035865, + "first_commit": "2021-07-03 14:44:06", + "latest_commit": "2021-07-03 10:44:10", "languages": [], "model_or_dataset": "model", "model_size": null, - "model_architectures": "DebertaV2ForTokenClassification" + "model_architectures": null }, { - "description": "roberta-large-japanese-aozora-char Model Description", - "url": "https://huggingface.co/KoichiYasuoka/roberta-large-japanese-aozora-char", - "project_name": "roberta-large-japanese-aozora-char", + "description": "モデルについて Qwen/Qwen1.5-0.5Bを日英データ5Bトークンで継続事前学習したモデルです。 ", + "url": "https://huggingface.co/Kendamarron/Tokara-0.5B-v0.1", + "project_name": "Tokara-0.5B-v0.1", "downloads": 11, "source": "Hugging Face", - "score": -0.11427307255156337, - "first_commit": "2021-12-30 14:19:53", - "latest_commit": "2022-06-22 10:22:43", + "score": -0.09267834812035865, + "first_commit": "2024-05-06 11:39:26", + "latest_commit": "2024-05-08 12:44:05", "languages": [], "model_or_dataset": "model", - "model_size": null, - "model_architectures": "RobertaForMaskedLM" + "model_size": 0.464, + "model_architectures": "Qwen2ForCausalLM" }, { - "description": "JP Voice-Text Dataset for", - "url": "https://huggingface.co/datasets/deepghs/fgo_voices_jp", - "project_name": "fgo_voices_jp", + "description": "A Japanese dataset generated with an opensource elyza/ELYZA-japanese-Llama-2-13b-instruct model.", + "url": "https://huggingface.co/datasets/iam-ajaymeena/Self-Instruct-Japanese-Elzya-13B", + "project_name": "Self-Instruct-Japanese-Elzya-13B", "downloads": 11, "source": "Hugging Face", - "score": -0.11427307255156337, - "first_commit": "2024-08-28 08:56:04", - "latest_commit": "2024-08-28 09:14:22", + "score": -0.09267834812035865, + "first_commit": "2024-06-15 08:11:55", + "latest_commit": "2024-06-16 09:12:56", "languages": [], "model_or_dataset": "dataset", "model_size": null, "model_architectures": null }, { - "description": "Dataset Details Dataset Type:Japanese LLaVA Pretrain is a localized version of the original LLaVA Pretrain dataset.", - "url": "https://huggingface.co/datasets/turing-motors/LLaVA-Pretrain-JA", - "project_name": "LLaVA-Pretrain-JA", - "downloads": 11, - "source": "Hugging Face", - "score": -0.11427307255156337, - "first_commit": "2024-04-10 05:07:24", - "latest_commit": "2024-04-12 09:15:37", + "description": "External dictionary importer for Yomichan.", + "url": "https://github.com/FooSoft/yomichan-import", + "project_name": "yomichan-import", + "stargazers_count": 82, + "source": "GitHub", + "score": -0.09503521009091288, + "first_commit": "2016-07-26 20:24:33", + "latest_commit": "2023-02-25 12:43:03", + "languages": [ + "Go" + ], + "model_or_dataset": null + }, + { + "description": "日英変換・英語略語展開のための IME 追加辞書 orange_book 日本語から英語への和英変換や英語略語の展開を Google 日本語入力や ATOK などで可能にする IME 拡張辞書", + "url": "https://github.com/peaceiris/google-ime-dictionary", + "project_name": "google-ime-dictionary", + "stargazers_count": 82, + "source": "GitHub", + "score": -0.09503521009091288, + "first_commit": "2018-09-13 01:54:32", + "latest_commit": "2023-01-16 10:47:31", "languages": [], - "model_or_dataset": "dataset", - "model_size": null, - "model_architectures": null + "model_or_dataset": "dataset" + }, + { + "description": "databricks/dolly-v2-12b の学習データに使用されたdatabricks-dolly-15k.jsonl を日本語に翻訳したデータセットになります。", + "url": "https://github.com/kunishou/databricks-dolly-15k-ja", + "project_name": "databricks-dolly-15k-ja", + "stargazers_count": 81, + "source": "GitHub", + "score": -0.09797523065218258, + "first_commit": "2023-04-14 23:43:27", + "latest_commit": "2023-07-26 00:08:32", + "languages": [], + "model_or_dataset": "dataset" + }, + { + "description": "Python library for CJK (Chinese, Japanese, and Korean) language dictionary", + "url": "https://github.com/cihai/cihai", + "project_name": "cihai", + "stargazers_count": 80, + "source": "GitHub", + "score": -0.1009152512134523, + "first_commit": "2013-12-03 09:42:52", + "latest_commit": "2024-08-10 13:13:53", + "languages": [ + "Python" + ], + "model_or_dataset": null + }, + { + "description": "Neologism dictionary based on the language resources on the Web for mecab-unidic", + "url": "https://github.com/neologd/mecab-unidic-neologd", + "project_name": "mecab-unidic-neologd", + "stargazers_count": 80, + "source": "GitHub", + "score": -0.1009152512134523, + "first_commit": "2015-03-19 10:52:02", + "latest_commit": "2020-09-14 19:58:39", + "languages": [], + "model_or_dataset": "dataset" + }, + { + "description": "Japanese Dictionary", + "url": "https://github.com/gojp/nihongo", + "project_name": "nihongo", + "stargazers_count": 78, + "source": "GitHub", + "score": -0.10679529233599169, + "first_commit": "2013-09-03 00:22:50", + "latest_commit": "2024-02-07 18:36:24", + "languages": [ + "Go", + "Python" + ], + "model_or_dataset": null + }, + { + "description": "A large parallel corpus of English and Japanese", + "url": "https://github.com/rpryzant/JESC", + "project_name": "JESC", + "stargazers_count": 78, + "source": "GitHub", + "score": -0.10679529233599169, + "first_commit": "2017-10-25 07:41:35", + "latest_commit": "2017-10-31 21:08:56", + "languages": [ + "Python" + ], + "model_or_dataset": "dataset" + }, + { + "description": "Japanese Morphological Analysis written in Rust", + "url": "https://github.com/Leko/goya", + "project_name": "goya", + "stargazers_count": 77, + "source": "GitHub", + "score": -0.1097353128972614, + "first_commit": "2021-09-08 19:51:11", + "latest_commit": "2021-12-30 19:44:15", + "languages": [ + "Rust", + "JavaScript", + "TypeScript" + ], + "model_or_dataset": null + }, + { + "description": "Japanese tokenizer for Transformers", + "url": "https://github.com/WorksApplications/SudachiTra", + "project_name": "SudachiTra", + "stargazers_count": 77, + "source": "GitHub", + "score": -0.1097353128972614, + "first_commit": "2021-06-22 19:48:29", + "latest_commit": "2023-12-15 08:13:45", + "languages": [ + "Python" + ], + "model_or_dataset": "model" + }, + { + "description": "UNICODE絵文字の日本語読み/キーワード/分類辞書", + "url": "https://github.com/yagays/emoji-ja", + "project_name": "emoji-ja", + "stargazers_count": 77, + "source": "GitHub", + "score": -0.1097353128972614, + "first_commit": "2018-08-24 08:25:08", + "latest_commit": "2023-05-09 14:57:44", + "languages": [ + "Python" + ], + "model_or_dataset": "dataset" }, { "description": "Kyoto University Web Document Leads Corpus", @@ -13479,7 +13871,7 @@ "project_name": "KWDLC", "stargazers_count": 75, "source": "GitHub", - "score": -0.11747244496233353, + "score": -0.1156153540198008, "first_commit": "2015-05-20 19:13:17", "latest_commit": "2023-12-18 14:13:14", "languages": [ @@ -13493,7 +13885,7 @@ "project_name": "llm-japanese-dataset", "stargazers_count": 75, "source": "GitHub", - "score": -0.11747244496233353, + "score": -0.1156153540198008, "first_commit": "2023-04-19 14:34:02", "latest_commit": "2024-01-23 09:37:30", "languages": [ @@ -13507,7 +13899,7 @@ "project_name": "jrte-corpus", "stargazers_count": 75, "source": "GitHub", - "score": -0.11747244496233353, + "score": -0.1156153540198008, "first_commit": "2020-10-15 14:59:37", "latest_commit": "2023-06-23 14:06:26", "languages": [ @@ -13521,7 +13913,7 @@ "project_name": "JMTrans", "stargazers_count": 74, "source": "GitHub", - "score": -0.12040398697493132, + "score": -0.1185553745810705, "first_commit": "2020-08-19 23:30:03", "latest_commit": "2021-01-16 21:44:37", "languages": [ @@ -13536,7 +13928,7 @@ "project_name": "Dialog", "stargazers_count": 73, "source": "GitHub", - "score": -0.12333552898752911, + "score": -0.12149539514234022, "first_commit": "2019-09-12 13:05:51", "latest_commit": "2020-10-01 17:25:08", "languages": [ @@ -13551,7 +13943,7 @@ "project_name": "jmdict-yomitan", "stargazers_count": 73, "source": "GitHub", - "score": -0.12333552898752911, + "score": -0.12149539514234022, "first_commit": "2023-09-24 20:01:40", "latest_commit": "2024-07-30 10:44:53", "languages": [ @@ -13565,7 +13957,7 @@ "project_name": "nlp100v2020", "stargazers_count": 73, "source": "GitHub", - "score": -0.12333552898752911, + "score": -0.12149539514234022, "first_commit": "2020-04-07 20:23:08", "latest_commit": "2023-11-05 23:36:07", "languages": [ @@ -13579,7 +13971,7 @@ "project_name": "Laboro-BERT-Japanese", "stargazers_count": 72, "source": "GitHub", - "score": -0.1262670710001269, + "score": -0.12443541570360991, "first_commit": "2020-03-31 12:05:07", "latest_commit": "2022-05-12 17:06:31", "languages": [ @@ -13593,7 +13985,7 @@ "project_name": "resembla", "stargazers_count": 71, "source": "GitHub", - "score": -0.12919861301272467, + "score": -0.12737543626487963, "first_commit": "2017-07-24 17:07:39", "latest_commit": "2019-01-27 00:08:52", "languages": [ @@ -13609,7 +14001,7 @@ "project_name": "unidic-py", "stargazers_count": 71, "source": "GitHub", - "score": -0.12919861301272467, + "score": -0.12737543626487963, "first_commit": "2020-01-05 16:19:49", "latest_commit": "2023-06-16 20:50:30", "languages": [ @@ -13623,7 +14015,7 @@ "project_name": "wikipedia-utils", "stargazers_count": 71, "source": "GitHub", - "score": -0.12919861301272467, + "score": -0.12737543626487963, "first_commit": "2022-01-09 16:42:14", "latest_commit": "2024-04-10 08:41:09", "languages": [ @@ -13637,7 +14029,7 @@ "project_name": "TinySegmenterMaker", "stargazers_count": 69, "source": "GitHub", - "score": -0.13506169703792026, + "score": -0.13325547738741902, "first_commit": "2012-11-15 22:24:06", "latest_commit": "2022-09-30 13:41:19", "languages": [ @@ -13659,7 +14051,7 @@ "project_name": "aozorabunko_text", "stargazers_count": 69, "source": "GitHub", - "score": -0.13506169703792026, + "score": -0.13325547738741902, "first_commit": "2019-02-11 03:06:07", "latest_commit": "2023-03-22 01:21:29", "languages": [ @@ -13673,7 +14065,7 @@ "project_name": "5ch-analysis", "stargazers_count": 67, "source": "GitHub", - "score": -0.14092478106311582, + "score": -0.13913551850995842, "first_commit": "2018-11-11 16:58:44", "latest_commit": "2018-11-11 23:37:16", "languages": [ @@ -13687,7 +14079,7 @@ "project_name": "wana_kana_rust", "stargazers_count": 67, "source": "GitHub", - "score": -0.14092478106311582, + "score": -0.13913551850995842, "first_commit": "2018-02-02 18:39:03", "latest_commit": "2023-01-19 21:51:26", "languages": [ @@ -13702,7 +14094,7 @@ "project_name": "japanese-clip", "stargazers_count": 66, "source": "GitHub", - "score": -0.1438563230757136, + "score": -0.14207553907122814, "first_commit": "2022-04-25 17:19:28", "latest_commit": "2022-07-19 18:20:52", "languages": [ @@ -13716,7 +14108,7 @@ "project_name": "dic-nico-intersection-pixiv", "stargazers_count": 66, "source": "GitHub", - "score": -0.1438563230757136, + "score": -0.14207553907122814, "first_commit": "2017-03-09 08:44:44", "latest_commit": "2024-04-19 13:29:16", "languages": [ @@ -13730,7 +14122,7 @@ "project_name": "mouse_over_dictionary", "stargazers_count": 66, "source": "GitHub", - "score": -0.1438563230757136, + "score": -0.14207553907122814, "first_commit": "2020-01-09 20:26:17", "latest_commit": "2020-01-24 08:57:39", "languages": [ @@ -13744,7 +14136,7 @@ "project_name": "BSD", "stargazers_count": 66, "source": "GitHub", - "score": -0.1438563230757136, + "score": -0.14207553907122814, "first_commit": "2020-07-25 01:04:11", "latest_commit": "2021-11-10 21:33:34", "languages": [], @@ -13756,7 +14148,7 @@ "project_name": "neural_ime", "stargazers_count": 65, "source": "GitHub", - "score": -0.1467878650883114, + "score": -0.14501555963249785, "first_commit": "2016-10-31 15:23:42", "latest_commit": "2016-12-27 21:10:30", "languages": [ @@ -13770,7 +14162,7 @@ "project_name": "cskk", "stargazers_count": 65, "source": "GitHub", - "score": -0.1467878650883114, + "score": -0.14501555963249785, "first_commit": "2018-06-17 15:36:26", "latest_commit": "2024-03-10 13:45:41", "languages": [ @@ -13785,7 +14177,7 @@ "project_name": "ibus-hiragana", "stargazers_count": 64, "source": "GitHub", - "score": -0.1497194071009092, + "score": -0.14795558019376753, "first_commit": "2017-04-28 03:50:59", "latest_commit": "2024-08-15 04:09:53", "languages": [ @@ -13799,7 +14191,7 @@ "project_name": "pdmocrdataset-part1", "stargazers_count": 64, "source": "GitHub", - "score": -0.1497194071009092, + "score": -0.14795558019376753, "first_commit": "2022-04-20 11:55:33", "latest_commit": "2024-06-26 16:10:44", "languages": [], @@ -13811,7 +14203,7 @@ "project_name": "ja_sentence_segmenter", "stargazers_count": 63, "source": "GitHub", - "score": -0.152650949113507, + "score": -0.15089560075503725, "first_commit": "2019-12-15 13:50:07", "latest_commit": "2023-04-03 13:09:20", "languages": [ @@ -13825,7 +14217,7 @@ "project_name": "daaja", "stargazers_count": 63, "source": "GitHub", - "score": -0.152650949113507, + "score": -0.15089560075503725, "first_commit": "2022-02-12 20:22:34", "latest_commit": "2023-02-16 19:39:30", "languages": [ @@ -13840,7 +14232,7 @@ "project_name": "nlp-recipes-ja", "stargazers_count": 63, "source": "GitHub", - "score": -0.152650949113507, + "score": -0.15089560075503725, "first_commit": "2020-08-01 09:09:07", "latest_commit": "2021-04-11 08:07:45", "languages": [ @@ -13855,7 +14247,7 @@ "project_name": "spacy_tutorial", "stargazers_count": 63, "source": "GitHub", - "score": -0.152650949113507, + "score": -0.15089560075503725, "first_commit": "2019-12-29 04:28:30", "latest_commit": "2020-01-24 20:02:24", "languages": [ @@ -13869,7 +14261,7 @@ "project_name": "gptuber-by-langchain", "stargazers_count": 62, "source": "GitHub", - "score": -0.15558249112610475, + "score": -0.15383562131630696, "first_commit": "2023-01-07 00:37:20", "latest_commit": "2023-01-07 00:37:20", "languages": [ @@ -13883,7 +14275,7 @@ "project_name": "gptuber-by-langchain", "stargazers_count": 62, "source": "GitHub", - "score": -0.15558249112610475, + "score": -0.15383562131630696, "first_commit": "2023-01-07 00:37:20", "latest_commit": "2023-01-07 00:37:20", "languages": [ @@ -13897,7 +14289,7 @@ "project_name": "fugumt", "stargazers_count": 61, "source": "GitHub", - "score": -0.15851403313870255, + "score": -0.15677564187757664, "first_commit": "2021-01-02 20:35:49", "latest_commit": "2021-02-28 11:46:52", "languages": [ @@ -13911,7 +14303,7 @@ "project_name": "jakaroma", "stargazers_count": 61, "source": "GitHub", - "score": -0.15851403313870255, + "score": -0.15677564187757664, "first_commit": "2016-04-11 18:21:38", "latest_commit": "2021-03-30 23:21:16", "languages": [ @@ -13925,7 +14317,7 @@ "project_name": "jageocoder", "stargazers_count": 60, "source": "GitHub", - "score": -0.16144557515130034, + "score": -0.15971566243884636, "first_commit": "2021-02-20 17:31:56", "latest_commit": "2024-07-03 06:01:58", "languages": [ @@ -13939,7 +14331,7 @@ "project_name": "llm-leaderboard", "stargazers_count": 60, "source": "GitHub", - "score": -0.16144557515130034, + "score": -0.15971566243884636, "first_commit": "2023-06-27 15:09:25", "latest_commit": "2024-08-07 00:38:16", "languages": [ @@ -13953,7 +14345,7 @@ "project_name": "chatgpt-slackbot", "stargazers_count": 60, "source": "GitHub", - "score": -0.16144557515130034, + "score": -0.15971566243884636, "first_commit": "2022-12-06 22:50:09", "latest_commit": "2024-07-22 18:50:41", "languages": [ @@ -13967,7 +14359,7 @@ "project_name": "IOB2Corpus", "stargazers_count": 60, "source": "GitHub", - "score": -0.16144557515130034, + "score": -0.15971566243884636, "first_commit": "2016-01-29 09:21:25", "latest_commit": "2020-02-25 09:34:11", "languages": [], @@ -13979,7 +14371,7 @@ "project_name": "japanese", "stargazers_count": 60, "source": "GitHub", - "score": -0.16144557515130034, + "score": -0.15971566243884636, "first_commit": "2018-09-13 21:10:10", "latest_commit": "2018-09-13 22:02:23", "languages": [], @@ -13991,7 +14383,7 @@ "project_name": "japanese-numerals-to-number", "stargazers_count": 58, "source": "GitHub", - "score": -0.1673086591764959, + "score": -0.16559570356138575, "first_commit": "2017-02-25 22:53:18", "latest_commit": "2023-02-17 01:34:12", "languages": [ @@ -14005,7 +14397,7 @@ "project_name": "simple-simcse-ja", "stargazers_count": 57, "source": "GitHub", - "score": -0.1702402011890937, + "score": -0.16853572412265547, "first_commit": "2022-11-11 19:05:53", "latest_commit": "2023-10-31 14:18:17", "languages": [ @@ -14019,7 +14411,7 @@ "project_name": "mecab-rs", "stargazers_count": 55, "source": "GitHub", - "score": -0.17610328521428928, + "score": -0.17441576524519486, "first_commit": "2015-04-19 09:30:14", "latest_commit": "2023-09-03 22:03:49", "languages": [ @@ -14033,7 +14425,7 @@ "project_name": "YouyakuMan", "stargazers_count": 53, "source": "GitHub", - "score": -0.18196636923948484, + "score": -0.1802958063677343, "first_commit": "2019-10-29 17:43:01", "latest_commit": "2020-09-02 13:37:05", "languages": [ @@ -14047,7 +14439,7 @@ "project_name": "dvorakjp-romantable", "stargazers_count": 53, "source": "GitHub", - "score": -0.18196636923948484, + "score": -0.1802958063677343, "first_commit": "2015-10-11 16:49:41", "latest_commit": "2024-06-24 12:24:34", "languages": [ @@ -14061,7 +14453,7 @@ "project_name": "mozcdict-ext", "stargazers_count": 52, "source": "GitHub", - "score": -0.18489791125208263, + "score": -0.18323582692900398, "first_commit": "2023-01-12 18:13:26", "latest_commit": "2024-07-13 17:37:43", "languages": [ @@ -14075,7 +14467,7 @@ "project_name": "japanese-lm-fin-harness", "stargazers_count": 51, "source": "GitHub", - "score": -0.18782945326468042, + "score": -0.1861758474902737, "first_commit": "2023-09-28 10:48:05", "latest_commit": "2024-08-07 13:01:57", "languages": [ @@ -14089,7 +14481,7 @@ "project_name": "kakasi-java", "stargazers_count": 51, "source": "GitHub", - "score": -0.18782945326468042, + "score": -0.1861758474902737, "first_commit": "2012-01-18 17:33:15", "latest_commit": "2016-04-13 15:56:34", "languages": [ @@ -14103,7 +14495,7 @@ "project_name": "chikkarpy", "stargazers_count": 50, "source": "GitHub", - "score": -0.19076099527727822, + "score": -0.1891158680515434, "first_commit": "2021-05-24 17:10:56", "latest_commit": "2022-02-07 15:11:36", "languages": [ @@ -14117,7 +14509,7 @@ "project_name": "Retrieval-based-Voice-Conversion-WebUI-JP-localization", "stargazers_count": 50, "source": "GitHub", - "score": -0.19076099527727822, + "score": -0.1891158680515434, "first_commit": "2023-03-27 17:59:11", "latest_commit": "2023-04-11 11:08:47", "languages": [ @@ -14132,7 +14524,7 @@ "project_name": "lindera-tantivy", "stargazers_count": 50, "source": "GitHub", - "score": -0.19076099527727822, + "score": -0.1891158680515434, "first_commit": "2020-02-19 10:37:34", "latest_commit": "2023-12-02 21:03:48", "languages": [ @@ -14146,7 +14538,7 @@ "project_name": "kuroshiro-analyzer-kuromoji", "stargazers_count": 50, "source": "GitHub", - "score": -0.19076099527727822, + "score": -0.1891158680515434, "first_commit": "2018-03-09 17:41:37", "latest_commit": "2018-08-05 12:41:55", "languages": [ @@ -14160,7 +14552,7 @@ "project_name": "yomichan-jlpt-vocab", "stargazers_count": 50, "source": "GitHub", - "score": -0.19076099527727822, + "score": -0.1891158680515434, "first_commit": "2021-09-01 18:36:57", "latest_commit": "2023-04-06 22:29:12", "languages": [ @@ -14174,7 +14566,7 @@ "project_name": "rohan4600", "stargazers_count": 50, "source": "GitHub", - "score": -0.19076099527727822, + "score": -0.1891158680515434, "first_commit": "2021-07-31 23:43:43", "latest_commit": "2023-02-01 12:51:29", "languages": [], @@ -14186,7 +14578,7 @@ "project_name": "fasttext-vs-word2vec-on-twitter-data", "stargazers_count": 49, "source": "GitHub", - "score": -0.19369253728987598, + "score": -0.19205588861281309, "first_commit": "2017-03-30 23:10:04", "latest_commit": "2017-08-23 10:53:09", "languages": [ @@ -14200,7 +14592,7 @@ "project_name": "embedrank", "stargazers_count": 48, "source": "GitHub", - "score": -0.19662407930247378, + "score": -0.1949959091740828, "first_commit": "2019-02-01 11:40:50", "latest_commit": "2019-03-19 09:05:41", "languages": [ @@ -14214,7 +14606,7 @@ "project_name": "japanese-llama-experiment", "stargazers_count": 48, "source": "GitHub", - "score": -0.19662407930247378, + "score": -0.1949959091740828, "first_commit": "2023-06-28 17:43:53", "latest_commit": "2024-03-10 23:31:45", "languages": [ @@ -14230,7 +14622,7 @@ "project_name": "esupar", "stargazers_count": 47, "source": "GitHub", - "score": -0.19955562131507157, + "score": -0.1979359297353525, "first_commit": "2021-09-18 07:28:30", "latest_commit": "2024-08-15 20:37:47", "languages": [ @@ -14245,7 +14637,7 @@ "project_name": "japanese-llm-ranking", "stargazers_count": 47, "source": "GitHub", - "score": -0.19955562131507157, + "score": -0.1979359297353525, "first_commit": "2023-06-28 18:31:52", "latest_commit": "2024-03-04 18:17:06", "languages": [ @@ -14260,7 +14652,7 @@ "project_name": "tinysegmenter", "stargazers_count": 47, "source": "GitHub", - "score": -0.19955562131507157, + "score": -0.1979359297353525, "first_commit": "2014-07-04 17:23:23", "latest_commit": "2015-11-03 21:49:19", "languages": [ @@ -14274,7 +14666,7 @@ "project_name": "jslingua", "stargazers_count": 47, "source": "GitHub", - "score": -0.19955562131507157, + "score": -0.1979359297353525, "first_commit": "2016-03-22 10:52:37", "latest_commit": "2023-10-19 22:01:23", "languages": [ @@ -14289,7 +14681,7 @@ "project_name": "LLaVA-JP", "stargazers_count": 46, "source": "GitHub", - "score": -0.20248716332766936, + "score": -0.2008759502966222, "first_commit": "2023-12-01 12:26:17", "latest_commit": "2024-06-05 23:42:35", "languages": [ @@ -14303,7 +14695,7 @@ "project_name": "language-pretraining", "stargazers_count": 46, "source": "GitHub", - "score": -0.20248716332766936, + "score": -0.2008759502966222, "first_commit": "2021-07-07 12:07:22", "latest_commit": "2023-05-19 23:15:30", "languages": [ @@ -14317,7 +14709,7 @@ "project_name": "azure-search-openai-demo", "stargazers_count": 46, "source": "GitHub", - "score": -0.20248716332766936, + "score": -0.2008759502966222, "first_commit": "2023-02-08 13:00:55", "latest_commit": "2023-12-07 18:16:07", "languages": [ @@ -14333,7 +14725,7 @@ "project_name": "jawiki-kana-kanji-dict", "stargazers_count": 46, "source": "GitHub", - "score": -0.20248716332766936, + "score": -0.2008759502966222, "first_commit": "2020-08-23 02:36:22", "latest_commit": "2024-08-09 14:54:51", "languages": [ @@ -14347,7 +14739,7 @@ "project_name": "google-ime-user-dictionary-ja-en", "stargazers_count": 45, "source": "GitHub", - "score": -0.20541870534026715, + "score": -0.2038159708578919, "first_commit": "2009-12-11 10:24:53", "latest_commit": "2016-12-23 19:44:09", "languages": [], @@ -14359,7 +14751,7 @@ "project_name": "LINE-DistilBERT-Japanese", "stargazers_count": 44, "source": "GitHub", - "score": -0.20835024735286492, + "score": -0.20675599141916162, "first_commit": "2023-03-09 18:50:06", "latest_commit": "2023-03-22 15:09:22", "languages": [], @@ -14371,7 +14763,7 @@ "project_name": "JSICK", "stargazers_count": 44, "source": "GitHub", - "score": -0.20835024735286492, + "score": -0.20675599141916162, "first_commit": "2021-05-24 18:12:15", "latest_commit": "2023-05-31 17:48:45", "languages": [], @@ -14383,7 +14775,7 @@ "project_name": "Convert-Numbers-to-Japanese", "stargazers_count": 43, "source": "GitHub", - "score": -0.2112817893654627, + "score": -0.2096960119804313, "first_commit": "2017-03-24 12:30:39", "latest_commit": "2020-11-26 16:37:30", "languages": [ @@ -14397,7 +14789,7 @@ "project_name": "japanese-daily-dialogue", "stargazers_count": 43, "source": "GitHub", - "score": -0.2112817893654627, + "score": -0.2096960119804313, "first_commit": "2023-03-15 16:53:41", "latest_commit": "2023-03-17 18:53:28", "languages": [], @@ -14409,7 +14801,7 @@ "project_name": "namaco", "stargazers_count": 41, "source": "GitHub", - "score": -0.2171448733906583, + "score": -0.21557605310297073, "first_commit": "2017-10-11 09:53:23", "latest_commit": "2018-02-09 06:27:36", "languages": [ @@ -14424,7 +14816,7 @@ "project_name": "llm-jp-sft", "stargazers_count": 41, "source": "GitHub", - "score": -0.2171448733906583, + "score": -0.21557605310297073, "first_commit": "2023-09-22 14:30:09", "latest_commit": "2024-06-13 13:17:38", "languages": [ @@ -14438,7 +14830,7 @@ "project_name": "node-romaji-name", "stargazers_count": 41, "source": "GitHub", - "score": -0.2171448733906583, + "score": -0.21557605310297073, "first_commit": "2013-08-24 10:50:11", "latest_commit": "2023-12-27 13:27:03", "languages": [ @@ -14452,7 +14844,7 @@ "project_name": "japanese-toolkit", "stargazers_count": 41, "source": "GitHub", - "score": -0.2171448733906583, + "score": -0.21557605310297073, "first_commit": "2020-07-09 05:58:18", "latest_commit": "2023-01-08 23:53:43", "languages": [ @@ -14467,7 +14859,7 @@ "project_name": "make-meidai-dialogue", "stargazers_count": 40, "source": "GitHub", - "score": -0.2200764154032561, + "score": -0.21851607366424042, "first_commit": "2016-11-10 13:45:38", "latest_commit": "2017-09-29 07:53:24", "languages": [ @@ -14481,7 +14873,7 @@ "project_name": "vits-japros-webui", "stargazers_count": 40, "source": "GitHub", - "score": -0.2200764154032561, + "score": -0.21851607366424042, "first_commit": "2023-09-30 17:09:14", "latest_commit": "2024-01-05 22:42:43", "languages": [ @@ -14497,7 +14889,7 @@ "project_name": "bert-japanese-aozora", "stargazers_count": 40, "source": "GitHub", - "score": -0.2200764154032561, + "score": -0.21851607366424042, "first_commit": "2020-03-08 10:20:43", "latest_commit": "2020-08-08 12:06:20", "languages": [], @@ -14509,7 +14901,7 @@ "project_name": "koniwa", "stargazers_count": 40, "source": "GitHub", - "score": -0.2200764154032561, + "score": -0.21851607366424042, "first_commit": "2021-10-29 21:19:06", "latest_commit": "2024-08-02 10:48:21", "languages": [ @@ -14524,7 +14916,7 @@ "project_name": "DocumentClassificationUsingBERT-Japanese", "stargazers_count": 40, "source": "GitHub", - "score": -0.2200764154032561, + "score": -0.21851607366424042, "first_commit": "2019-12-16 00:55:48", "latest_commit": "2021-01-29 10:59:18", "languages": [ @@ -14539,7 +14931,7 @@ "project_name": "Japanese-BPEEncoder", "stargazers_count": 39, "source": "GitHub", - "score": -0.22300795741585386, + "score": -0.22145609422551013, "first_commit": "2020-10-03 12:21:03", "latest_commit": "2021-09-12 09:58:42", "languages": [ @@ -14553,7 +14945,7 @@ "project_name": "kanjigrid", "stargazers_count": 39, "source": "GitHub", - "score": -0.22300795741585386, + "score": -0.22145609422551013, "first_commit": "2018-10-26 15:47:29", "latest_commit": "2018-11-19 14:14:00", "languages": [ @@ -14567,7 +14959,7 @@ "project_name": "t5-japanese", "stargazers_count": 39, "source": "GitHub", - "score": -0.22300795741585386, + "score": -0.22145609422551013, "first_commit": "2021-08-25 09:55:16", "latest_commit": "2021-09-07 14:11:02", "languages": [ @@ -14581,7 +14973,7 @@ "project_name": "emoticon", "stargazers_count": 39, "source": "GitHub", - "score": -0.22300795741585386, + "score": -0.22145609422551013, "first_commit": "2013-12-29 17:16:16", "latest_commit": "2020-05-07 13:36:42", "languages": [ @@ -14595,7 +14987,7 @@ "project_name": "llm-jp-corpus", "stargazers_count": 39, "source": "GitHub", - "score": -0.22300795741585386, + "score": -0.22145609422551013, "first_commit": "2023-06-14 13:21:33", "latest_commit": "2023-10-23 10:04:18", "languages": [ @@ -14609,7 +15001,7 @@ "project_name": "xvector_jtubespeech", "stargazers_count": 38, "source": "GitHub", - "score": -0.22593949942845165, + "score": -0.22439611478677984, "first_commit": "2022-03-08 11:00:20", "latest_commit": "2023-11-05 14:48:26", "languages": [ @@ -14623,7 +15015,7 @@ "project_name": "IgakuQA", "stargazers_count": 38, "source": "GitHub", - "score": -0.22593949942845165, + "score": -0.22439611478677984, "first_commit": "2023-03-31 10:29:20", "latest_commit": "2023-03-31 10:29:20", "languages": [ @@ -14637,7 +15029,7 @@ "project_name": "Japanese-BPEEncoder_V2", "stargazers_count": 37, "source": "GitHub", - "score": -0.22887104144104944, + "score": -0.22733613534804953, "first_commit": "2021-08-23 19:09:11", "latest_commit": "2023-01-15 12:43:44", "languages": [ @@ -14651,7 +15043,7 @@ "project_name": "Mykytea-python", "stargazers_count": 36, "source": "GitHub", - "score": -0.23180258345364724, + "score": -0.23027615590931924, "first_commit": "2011-07-15 11:45:10", "latest_commit": "2024-01-15 17:30:17", "languages": [ @@ -14666,7 +15058,7 @@ "project_name": "handwritten-japanese-ocr", "stargazers_count": 36, "source": "GitHub", - "score": -0.23180258345364724, + "score": -0.23027615590931924, "first_commit": "2020-05-01 17:27:13", "latest_commit": "2022-04-05 11:16:31", "languages": [ @@ -14681,7 +15073,7 @@ "project_name": "japanese-llm-roleplay-benchmark", "stargazers_count": 36, "source": "GitHub", - "score": -0.23180258345364724, + "score": -0.23027615590931924, "first_commit": "2023-09-15 23:52:27", "latest_commit": "2023-11-03 22:01:24", "languages": [ @@ -14696,7 +15088,7 @@ "project_name": "python-vibrato", "stargazers_count": 35, "source": "GitHub", - "score": -0.234734125466245, + "score": -0.23321617647058893, "first_commit": "2022-12-08 12:29:38", "latest_commit": "2023-09-05 22:16:59", "languages": [ @@ -14711,7 +15103,7 @@ "project_name": "mozcpy", "stargazers_count": 35, "source": "GitHub", - "score": -0.234734125466245, + "score": -0.23321617647058893, "first_commit": "2022-08-21 02:20:37", "latest_commit": "2023-12-12 00:56:24", "languages": [ @@ -14725,7 +15117,7 @@ "project_name": "ja-tokenizer-docker-py", "stargazers_count": 35, "source": "GitHub", - "score": -0.234734125466245, + "score": -0.23321617647058893, "first_commit": "2022-05-08 13:45:30", "latest_commit": "2022-05-10 16:55:48", "languages": [ @@ -14740,7 +15132,7 @@ "project_name": "JIWC-Dictionary", "stargazers_count": 35, "source": "GitHub", - "score": -0.234734125466245, + "score": -0.23321617647058893, "first_commit": "2020-07-31 16:28:26", "latest_commit": "2021-01-27 17:39:40", "languages": [], @@ -14752,7 +15144,7 @@ "project_name": "wikihow_japanese", "stargazers_count": 35, "source": "GitHub", - "score": -0.234734125466245, + "score": -0.23321617647058893, "first_commit": "2020-06-29 03:11:23", "latest_commit": "2020-12-18 03:54:55", "languages": [ @@ -14766,7 +15158,7 @@ "project_name": "react-native-japanese-tokenizer", "stargazers_count": 34, "source": "GitHub", - "score": -0.2376656674788428, + "score": -0.23615619703185864, "first_commit": "2018-03-14 15:07:47", "latest_commit": "2023-06-19 09:34:01", "languages": [ @@ -14781,7 +15173,7 @@ "project_name": "pytorch_bert_japanese", "stargazers_count": 34, "source": "GitHub", - "score": -0.2376656674788428, + "score": -0.23615619703185864, "first_commit": "2019-06-05 21:42:27", "latest_commit": "2019-06-07 14:27:41", "languages": [ @@ -14795,7 +15187,7 @@ "project_name": "nayose-wikipedia-ja", "stargazers_count": 34, "source": "GitHub", - "score": -0.2376656674788428, + "score": -0.23615619703185864, "first_commit": "2020-03-09 09:16:39", "latest_commit": "2020-03-10 11:04:36", "languages": [ @@ -14809,7 +15201,7 @@ "project_name": "python-npylm", "stargazers_count": 33, "source": "GitHub", - "score": -0.2405972094914406, + "score": -0.23909621759312835, "first_commit": "2016-12-18 21:03:18", "latest_commit": "2019-01-30 16:35:14", "languages": [ @@ -14824,7 +15216,7 @@ "project_name": "EN-JP-ML-Lexicon", "stargazers_count": 33, "source": "GitHub", - "score": -0.2405972094914406, + "score": -0.23909621759312835, "first_commit": "2019-05-27 16:29:35", "latest_commit": "2021-03-13 09:19:56", "languages": [], @@ -14836,7 +15228,7 @@ "project_name": "albert-japanese", "stargazers_count": 33, "source": "GitHub", - "score": -0.2405972094914406, + "score": -0.23909621759312835, "first_commit": "2018-12-27 20:05:33", "latest_commit": "2021-10-28 19:57:23", "languages": [ @@ -14851,7 +15243,7 @@ "project_name": "pva-aoai-integration-solution", "stargazers_count": 33, "source": "GitHub", - "score": -0.2405972094914406, + "score": -0.23909621759312835, "first_commit": "2023-06-20 13:50:54", "latest_commit": "2023-08-14 18:03:34", "languages": [], @@ -14863,7 +15255,7 @@ "project_name": "unidic-lite", "stargazers_count": 33, "source": "GitHub", - "score": -0.2405972094914406, + "score": -0.23909621759312835, "first_commit": "2020-04-07 16:24:18", "latest_commit": "2020-09-01 22:50:07", "languages": [ @@ -14877,7 +15269,7 @@ "project_name": "UniDic2UD", "stargazers_count": 32, "source": "GitHub", - "score": -0.24352875150403838, + "score": -0.24203623815439804, "first_commit": "2019-08-27 00:45:01", "latest_commit": "2024-01-31 23:53:51", "languages": [ @@ -14892,7 +15284,7 @@ "project_name": "ja-vicuna-qa-benchmark", "stargazers_count": 32, "source": "GitHub", - "score": -0.24352875150403838, + "score": -0.24203623815439804, "first_commit": "2023-08-11 15:38:05", "latest_commit": "2024-06-11 16:24:06", "languages": [ @@ -14906,7 +15298,7 @@ "project_name": "text2text-japanese", "stargazers_count": 32, "source": "GitHub", - "score": -0.24352875150403838, + "score": -0.24203623815439804, "first_commit": "2021-02-11 12:28:53", "latest_commit": "2021-07-22 14:26:45", "languages": [ @@ -14920,7 +15312,7 @@ "project_name": "simple-jppdb", "stargazers_count": 32, "source": "GitHub", - "score": -0.24352875150403838, + "score": -0.24203623815439804, "first_commit": "2017-03-09 19:29:19", "latest_commit": "2017-03-13 00:01:48", "languages": [ @@ -14934,7 +15326,7 @@ "project_name": "whisper-asr-finetune", "stargazers_count": 31, "source": "GitHub", - "score": -0.24646029351663618, + "score": -0.24497625871566775, "first_commit": "2022-10-27 20:22:00", "latest_commit": "2022-12-04 21:29:47", "languages": [ @@ -14948,7 +15340,7 @@ "project_name": "moji4j", "stargazers_count": 31, "source": "GitHub", - "score": -0.24646029351663618, + "score": -0.24497625871566775, "first_commit": "2016-07-08 09:13:16", "latest_commit": "2022-06-24 09:00:44", "languages": [ @@ -14963,7 +15355,7 @@ "project_name": "jvs_hiho", "stargazers_count": 31, "source": "GitHub", - "score": -0.24646029351663618, + "score": -0.24497625871566775, "first_commit": "2020-02-02 01:24:43", "latest_commit": "2021-02-11 15:29:19", "languages": [], @@ -14975,7 +15367,7 @@ "project_name": "janome-tutorial", "stargazers_count": 31, "source": "GitHub", - "score": -0.24646029351663618, + "score": -0.24497625871566775, "first_commit": "2019-03-03 15:25:08", "latest_commit": "2019-03-03 16:46:00", "languages": [ @@ -14991,7 +15383,7 @@ "project_name": "marine", "stargazers_count": 30, "source": "GitHub", - "score": -0.24939183552923394, + "score": -0.24791627927693746, "first_commit": "2022-09-05 20:23:40", "latest_commit": "2022-09-20 10:26:24", "languages": [ @@ -15005,7 +15397,7 @@ "project_name": "ThreeLineSummaryDataset", "stargazers_count": 30, "source": "GitHub", - "score": -0.24939183552923394, + "score": -0.24791627927693746, "first_commit": "2018-01-25 02:27:22", "latest_commit": "2018-04-04 22:24:47", "languages": [], @@ -15017,7 +15409,7 @@ "project_name": "data_set", "stargazers_count": 30, "source": "GitHub", - "score": -0.24939183552923394, + "score": -0.24791627927693746, "first_commit": "2023-01-15 08:39:44", "latest_commit": "2024-05-14 17:37:05", "languages": [], @@ -15029,7 +15421,7 @@ "project_name": "rhoknp", "stargazers_count": 29, "source": "GitHub", - "score": -0.25232337754183176, + "score": -0.2508562998382072, "first_commit": "2021-08-03 14:50:30", "latest_commit": "2024-07-16 09:26:45", "languages": [ @@ -15044,7 +15436,7 @@ "project_name": "knp", "stargazers_count": 29, "source": "GitHub", - "score": -0.25232337754183176, + "score": -0.2508562998382072, "first_commit": "1999-03-12 09:09:08", "latest_commit": "2023-11-01 21:02:34", "languages": [ @@ -15064,7 +15456,7 @@ "project_name": "elasticsearch-analysis-japanese", "stargazers_count": 29, "source": "GitHub", - "score": -0.25232337754183176, + "score": -0.2508562998382072, "first_commit": "2012-01-11 13:32:35", "latest_commit": "2012-03-06 23:36:46", "languages": [ @@ -15078,7 +15470,7 @@ "project_name": "nijisanji-ime-dic", "stargazers_count": 29, "source": "GitHub", - "score": -0.25232337754183176, + "score": -0.2508562998382072, "first_commit": "2019-12-30 01:37:16", "latest_commit": "2024-08-14 12:35:13", "languages": [], @@ -15090,7 +15482,7 @@ "project_name": "anthy-unicode", "stargazers_count": 29, "source": "GitHub", - "score": -0.25232337754183176, + "score": -0.2508562998382072, "first_commit": "2013-06-30 11:09:24", "latest_commit": "2024-05-02 14:12:10", "languages": [ @@ -15104,7 +15496,7 @@ "project_name": "BERT_Japanese_Google_Colaboratory", "stargazers_count": 29, "source": "GitHub", - "score": -0.25232337754183176, + "score": -0.2508562998382072, "first_commit": "2020-05-14 14:53:17", "latest_commit": "2022-01-25 11:58:44", "languages": [ @@ -15118,7 +15510,7 @@ "project_name": "bert", "stargazers_count": 28, "source": "GitHub", - "score": -0.2552549195544295, + "score": -0.25379632039947686, "first_commit": "2022-04-05 17:03:10", "latest_commit": "2022-04-05 17:03:55", "languages": [ @@ -15132,7 +15524,7 @@ "project_name": "UD_Japanese-GSD", "stargazers_count": 28, "source": "GitHub", - "score": -0.2552549195544295, + "score": -0.25379632039947686, "first_commit": "2016-10-12 10:33:42", "latest_commit": "2022-05-29 11:52:21", "languages": [ @@ -15146,7 +15538,7 @@ "project_name": "comet-atomic-ja", "stargazers_count": 28, "source": "GitHub", - "score": -0.2552549195544295, + "score": -0.25379632039947686, "first_commit": "2023-02-04 10:39:44", "latest_commit": "2024-03-08 22:31:37", "languages": [ @@ -15160,7 +15552,7 @@ "project_name": "transformer-copy", "stargazers_count": 27, "source": "GitHub", - "score": -0.2581864615670273, + "score": -0.25673634096074655, "first_commit": "2019-08-24 23:18:00", "latest_commit": "2020-09-25 23:12:54", "languages": [ @@ -15176,7 +15568,7 @@ "project_name": "crawdad", "stargazers_count": 27, "source": "GitHub", - "score": -0.2581864615670273, + "score": -0.25673634096074655, "first_commit": "2022-03-20 23:22:50", "latest_commit": "2023-02-20 22:23:22", "languages": [ @@ -15190,7 +15582,7 @@ "project_name": "jpreprocess", "stargazers_count": 27, "source": "GitHub", - "score": -0.2581864615670273, + "score": -0.25673634096074655, "first_commit": "2022-12-18 17:32:12", "latest_commit": "2024-08-14 09:22:07", "languages": [ @@ -15206,7 +15598,7 @@ "project_name": "Japanese_nlp_scripts", "stargazers_count": 26, "source": "GitHub", - "score": -0.2611180035796251, + "score": -0.2596763615220163, "first_commit": "2015-05-18 17:15:00", "latest_commit": "2019-06-30 18:33:13", "languages": [ @@ -15220,7 +15612,7 @@ "project_name": "yoin", "stargazers_count": 26, "source": "GitHub", - "score": -0.2611180035796251, + "score": -0.2596763615220163, "first_commit": "2017-01-15 23:54:52", "latest_commit": "2017-10-27 17:44:55", "languages": [ @@ -15234,7 +15626,7 @@ "project_name": "imas-ime-dic", "stargazers_count": 26, "source": "GitHub", - "score": -0.2611180035796251, + "score": -0.2596763615220163, "first_commit": "2018-04-25 02:07:26", "latest_commit": "2024-04-19 01:05:34", "languages": [ @@ -15248,7 +15640,7 @@ "project_name": "security_words", "stargazers_count": 26, "source": "GitHub", - "score": -0.2611180035796251, + "score": -0.2596763615220163, "first_commit": "2020-04-27 12:23:28", "latest_commit": "2023-08-18 10:02:08", "languages": [], @@ -15260,7 +15652,7 @@ "project_name": "yomikata", "stargazers_count": 25, "source": "GitHub", - "score": -0.2640495455922229, + "score": -0.26261638208328597, "first_commit": "2023-02-21 01:43:00", "latest_commit": "2023-10-03 09:10:45", "languages": [ @@ -15275,7 +15667,7 @@ "project_name": "nksnd", "stargazers_count": 25, "source": "GitHub", - "score": -0.2640495455922229, + "score": -0.26261638208328597, "first_commit": "2016-05-24 18:52:03", "latest_commit": "2018-05-17 08:54:24", "languages": [ @@ -15289,7 +15681,7 @@ "project_name": "tweetMapping", "stargazers_count": 25, "source": "GitHub", - "score": -0.2640495455922229, + "score": -0.26261638208328597, "first_commit": "2021-02-17 07:55:27", "latest_commit": "2023-12-08 21:42:44", "languages": [ @@ -15303,7 +15695,7 @@ "project_name": "ipadic-py", "stargazers_count": 25, "source": "GitHub", - "score": -0.2640495455922229, + "score": -0.26261638208328597, "first_commit": "2020-07-16 16:19:26", "latest_commit": "2021-10-31 04:47:19", "languages": [ @@ -15317,7 +15709,7 @@ "project_name": "JMRD", "stargazers_count": 25, "source": "GitHub", - "score": -0.2640495455922229, + "score": -0.26261638208328597, "first_commit": "2022-07-15 09:43:44", "latest_commit": "2022-07-19 10:02:29", "languages": [], @@ -15329,7 +15721,7 @@ "project_name": "vrchatbot", "stargazers_count": 24, "source": "GitHub", - "score": -0.2669810876048207, + "score": -0.26555640264455566, "first_commit": "2022-12-10 22:48:39", "latest_commit": "2022-12-20 17:18:44", "languages": [ @@ -15343,7 +15735,7 @@ "project_name": "llm-jp-tokenizer", "stargazers_count": 23, "source": "GitHub", - "score": -0.26991262961741846, + "score": -0.2684964232058254, "first_commit": "2023-07-13 12:52:22", "latest_commit": "2024-07-05 13:56:54", "languages": [ @@ -15357,7 +15749,7 @@ "project_name": "python_asa", "stargazers_count": 23, "source": "GitHub", - "score": -0.26991262961741846, + "score": -0.2684964232058254, "first_commit": "2018-07-25 04:13:21", "latest_commit": "2020-01-14 17:09:11", "languages": [ @@ -15371,7 +15763,7 @@ "project_name": "hatsuon", "stargazers_count": 23, "source": "GitHub", - "score": -0.26991262961741846, + "score": -0.2684964232058254, "first_commit": "2018-04-06 12:06:12", "latest_commit": "2022-03-14 18:06:39", "languages": [ @@ -15385,7 +15777,7 @@ "project_name": "AISisterAIChan", "stargazers_count": 23, "source": "GitHub", - "score": -0.26991262961741846, + "score": -0.2684964232058254, "first_commit": "2023-03-30 18:40:44", "latest_commit": "2023-05-18 22:14:24", "languages": [], @@ -15397,7 +15789,7 @@ "project_name": "cl-skkserv", "stargazers_count": 23, "source": "GitHub", - "score": -0.26991262961741846, + "score": -0.2684964232058254, "first_commit": "2017-12-23 10:20:54", "latest_commit": "2024-02-11 10:42:23", "languages": [], @@ -15409,7 +15801,7 @@ "project_name": "asdc", "stargazers_count": 23, "source": "GitHub", - "score": -0.26991262961741846, + "score": -0.2684964232058254, "first_commit": "2022-06-16 09:43:01", "latest_commit": "2023-08-09 12:03:48", "languages": [ @@ -15423,7 +15815,7 @@ "project_name": "rakutenma-python", "stargazers_count": 22, "source": "GitHub", - "score": -0.27284417163001623, + "score": -0.2714364437670951, "first_commit": "2015-01-02 06:52:27", "latest_commit": "2017-05-22 16:45:10", "languages": [ @@ -15437,7 +15829,7 @@ "project_name": "bertknp", "stargazers_count": 22, "source": "GitHub", - "score": -0.27284417163001623, + "score": -0.2714364437670951, "first_commit": "2021-02-10 09:20:17", "latest_commit": "2021-10-02 14:45:12", "languages": [ @@ -15451,7 +15843,7 @@ "project_name": "ILYS-aoba-chatbot", "stargazers_count": 22, "source": "GitHub", - "score": -0.27284417163001623, + "score": -0.2714364437670951, "first_commit": "2020-10-26 13:13:33", "latest_commit": "2021-10-01 22:55:52", "languages": [ @@ -15467,7 +15859,7 @@ "project_name": "RoBERTa-japanese", "stargazers_count": 22, "source": "GitHub", - "score": -0.27284417163001623, + "score": -0.2714364437670951, "first_commit": "2020-11-28 17:36:50", "latest_commit": "2021-11-13 10:37:23", "languages": [ @@ -15481,7 +15873,7 @@ "project_name": "jisyo", "stargazers_count": 22, "source": "GitHub", - "score": -0.27284417163001623, + "score": -0.2714364437670951, "first_commit": null, "latest_commit": null, "languages": [], @@ -15493,7 +15885,7 @@ "project_name": "instruction_ja", "stargazers_count": 22, "source": "GitHub", - "score": -0.27284417163001623, + "score": -0.2714364437670951, "first_commit": "2023-06-22 15:52:12", "latest_commit": "2023-07-13 16:02:15", "languages": [ @@ -15507,7 +15899,7 @@ "project_name": "sengiri", "stargazers_count": 21, "source": "GitHub", - "score": -0.27577571364261405, + "score": -0.27437646432836477, "first_commit": "2019-10-05 03:46:43", "latest_commit": "2022-08-10 20:45:00", "languages": [ @@ -15521,7 +15913,7 @@ "project_name": "rake-ja", "stargazers_count": 21, "source": "GitHub", - "score": -0.27577571364261405, + "score": -0.27437646432836477, "first_commit": "2018-10-11 19:07:50", "latest_commit": "2018-10-11 19:27:37", "languages": [ @@ -15535,7 +15927,7 @@ "project_name": "rime-jaroomaji", "stargazers_count": 21, "source": "GitHub", - "score": -0.27577571364261405, + "score": -0.27437646432836477, "first_commit": "2023-03-21 21:07:42", "latest_commit": "2024-08-15 11:40:00", "languages": [ @@ -15549,7 +15941,7 @@ "project_name": "TwitterCorpus", "stargazers_count": 21, "source": "GitHub", - "score": -0.27577571364261405, + "score": -0.27437646432836477, "first_commit": "2016-03-05 19:20:15", "latest_commit": "2016-03-14 19:55:35", "languages": [ @@ -15563,7 +15955,7 @@ "project_name": "do-not-answer-ja", "stargazers_count": 21, "source": "GitHub", - "score": -0.27577571364261405, + "score": -0.27437646432836477, "first_commit": "2023-09-09 08:21:26", "latest_commit": "2023-12-16 02:34:12", "languages": [ @@ -15578,7 +15970,7 @@ "project_name": "kantan-regex-book", "stargazers_count": 21, "source": "GitHub", - "score": -0.27577571364261405, + "score": -0.27437646432836477, "first_commit": "2024-01-28 10:37:12", "latest_commit": "2024-03-23 21:55:27", "languages": [ @@ -15593,7 +15985,7 @@ "project_name": "python-vaporetto", "stargazers_count": 20, "source": "GitHub", - "score": -0.2787072556552118, + "score": -0.2773164848896345, "first_commit": "2022-06-09 13:37:22", "latest_commit": "2023-09-05 22:15:48", "languages": [ @@ -15608,7 +16000,7 @@ "project_name": "darts-clone-python", "stargazers_count": 20, "source": "GitHub", - "score": -0.2787072556552118, + "score": -0.2773164848896345, "first_commit": "2018-11-17 00:57:52", "latest_commit": "2022-04-05 21:28:21", "languages": [ @@ -15622,7 +16014,7 @@ "project_name": "text-generation", "stargazers_count": 20, "source": "GitHub", - "score": -0.2787072556552118, + "score": -0.2773164848896345, "first_commit": "2022-07-17 11:55:29", "latest_commit": "2022-07-24 13:48:32", "languages": [ @@ -15637,7 +16029,7 @@ "project_name": "keigo_transfer_task", "stargazers_count": 20, "source": "GitHub", - "score": -0.2787072556552118, + "score": -0.2773164848896345, "first_commit": "2022-06-14 23:06:57", "latest_commit": "2022-11-24 13:01:06", "languages": [], @@ -15649,7 +16041,7 @@ "project_name": "JMMLU", "stargazers_count": 20, "source": "GitHub", - "score": -0.2787072556552118, + "score": -0.2773164848896345, "first_commit": "2024-01-09 16:43:45", "latest_commit": "2024-02-27 14:19:14", "languages": [], @@ -15661,7 +16053,7 @@ "project_name": "jntajis-python", "stargazers_count": 19, "source": "GitHub", - "score": -0.2816387976678096, + "score": -0.2802565054509042, "first_commit": "2021-08-20 17:32:20", "latest_commit": "2023-06-16 22:43:41", "languages": [ @@ -15676,7 +16068,7 @@ "project_name": "pygeonlp", "stargazers_count": 19, "source": "GitHub", - "score": -0.2816387976678096, + "score": -0.2802565054509042, "first_commit": "2021-06-26 17:45:22", "latest_commit": "2024-07-24 01:39:27", "languages": [ @@ -15691,7 +16083,7 @@ "project_name": "unicode-jp-rs", "stargazers_count": 19, "source": "GitHub", - "score": -0.2816387976678096, + "score": -0.2802565054509042, "first_commit": "2016-05-21 16:39:49", "latest_commit": "2020-04-11 12:01:21", "languages": [ @@ -15705,7 +16097,7 @@ "project_name": "kyujitai.js", "stargazers_count": 19, "source": "GitHub", - "score": -0.2816387976678096, + "score": -0.2802565054509042, "first_commit": "2014-09-06 17:03:02", "latest_commit": "2020-08-30 23:28:58", "languages": [ @@ -15719,7 +16111,7 @@ "project_name": "go-moji", "stargazers_count": 19, "source": "GitHub", - "score": -0.2816387976678096, + "score": -0.2802565054509042, "first_commit": "2018-01-15 23:57:06", "latest_commit": "2019-04-17 10:29:44", "languages": [ @@ -15733,7 +16125,7 @@ "project_name": "huriganacorpus-ndlbib", "stargazers_count": 19, "source": "GitHub", - "score": -0.2816387976678096, + "score": -0.2802565054509042, "first_commit": "2021-09-01 13:36:53", "latest_commit": "2021-09-21 14:20:03", "languages": [], @@ -15745,7 +16137,7 @@ "project_name": "japanese-toxic-dataset", "stargazers_count": 19, "source": "GitHub", - "score": -0.2816387976678096, + "score": -0.2802565054509042, "first_commit": "2023-01-10 17:19:58", "latest_commit": "2023-01-11 13:55:08", "languages": [], @@ -15757,7 +16149,7 @@ "project_name": "camera", "stargazers_count": 19, "source": "GitHub", - "score": -0.2816387976678096, + "score": -0.2802565054509042, "first_commit": "2023-02-22 10:33:39", "latest_commit": "2024-08-13 09:20:33", "languages": [], @@ -15769,7 +16161,7 @@ "project_name": "Japanese-Fakenews-Dataset", "stargazers_count": 19, "source": "GitHub", - "score": -0.2816387976678096, + "score": -0.2802565054509042, "first_commit": "2021-05-02 15:40:10", "latest_commit": "2021-05-02 15:40:10", "languages": [], @@ -15781,7 +16173,7 @@ "project_name": "aozorasearch", "stargazers_count": 19, "source": "GitHub", - "score": -0.2816387976678096, + "score": -0.2802565054509042, "first_commit": "2016-10-15 17:22:45", "latest_commit": "2020-09-04 14:28:15", "languages": [ @@ -15796,7 +16188,7 @@ "project_name": "jqara", "stargazers_count": 19, "source": "GitHub", - "score": -0.2816387976678096, + "score": -0.2802565054509042, "first_commit": "2024-03-02 09:09:08", "latest_commit": "2024-08-10 11:54:50", "languages": [ @@ -15810,7 +16202,7 @@ "project_name": "jacwir", "stargazers_count": 19, "source": "GitHub", - "score": -0.2816387976678096, + "score": -0.2802565054509042, "first_commit": "2024-03-19 15:31:13", "latest_commit": "2024-07-24 11:09:03", "languages": [ @@ -15824,7 +16216,7 @@ "project_name": "japanese-numbers-python", "stargazers_count": 18, "source": "GitHub", - "score": -0.2845703396804074, + "score": -0.2831965260121739, "first_commit": "2016-07-29 09:20:05", "latest_commit": "2020-04-04 10:36:27", "languages": [ @@ -15838,7 +16230,7 @@ "project_name": "Grongish", "stargazers_count": 18, "source": "GitHub", - "score": -0.2845703396804074, + "score": -0.2831965260121739, "first_commit": "2012-02-10 22:28:59", "latest_commit": "2022-04-21 21:31:37", "languages": [ @@ -15853,7 +16245,7 @@ "project_name": "termextract", "stargazers_count": 18, "source": "GitHub", - "score": -0.2845703396804074, + "score": -0.2831965260121739, "first_commit": "2018-09-26 22:20:04", "latest_commit": "2018-09-26 23:01:36", "languages": [ @@ -15867,7 +16259,7 @@ "project_name": "minimal-search-engine", "stargazers_count": 18, "source": "GitHub", - "score": -0.2845703396804074, + "score": -0.2831965260121739, "first_commit": "2019-06-25 01:58:26", "latest_commit": "2019-07-06 01:26:57", "languages": [ @@ -15881,7 +16273,7 @@ "project_name": "mozcdic-ut-jawiki", "stargazers_count": 18, "source": "GitHub", - "score": -0.2845703396804074, + "score": -0.2831965260121739, "first_commit": "2023-01-15 17:43:20", "latest_commit": "2024-07-29 01:27:13", "languages": [ @@ -15895,7 +16287,7 @@ "project_name": "analyze-desumasu-dearu", "stargazers_count": 18, "source": "GitHub", - "score": -0.2845703396804074, + "score": -0.2831965260121739, "first_commit": "2015-10-10 01:42:33", "latest_commit": "2021-12-10 12:01:50", "languages": [ @@ -15909,7 +16301,7 @@ "project_name": "JaNLI", "stargazers_count": 18, "source": "GitHub", - "score": -0.2845703396804074, + "score": -0.2831965260121739, "first_commit": "2021-11-02 20:26:27", "latest_commit": "2023-05-31 17:50:04", "languages": [ @@ -15923,7 +16315,7 @@ "project_name": "technological-book-corpus-ja", "stargazers_count": 18, "source": "GitHub", - "score": -0.2845703396804074, + "score": -0.2831965260121739, "first_commit": "2017-03-26 13:28:13", "latest_commit": "2023-07-12 03:26:27", "languages": [ @@ -15937,7 +16329,7 @@ "project_name": "rinna_gpt-neox_ggml-lora", "stargazers_count": 17, "source": "GitHub", - "score": -0.28750188169300517, + "score": -0.2861365465734436, "first_commit": "2023-05-24 03:21:40", "latest_commit": "2023-05-25 05:38:04", "languages": [ @@ -15951,7 +16343,7 @@ "project_name": "chainer_nic", "stargazers_count": 17, "source": "GitHub", - "score": -0.28750188169300517, + "score": -0.2861365465734436, "first_commit": "2018-07-02 19:57:17", "latest_commit": "2018-12-14 17:26:49", "languages": [ @@ -15965,7 +16357,7 @@ "project_name": "yomigana-ebook", "stargazers_count": 17, "source": "GitHub", - "score": -0.28750188169300517, + "score": -0.2861365465734436, "first_commit": "2023-04-25 18:21:37", "latest_commit": "2024-02-21 01:18:17", "languages": [ @@ -15980,7 +16372,7 @@ "project_name": "jmteb", "stargazers_count": 17, "source": "GitHub", - "score": -0.28750188169300517, + "score": -0.2861365465734436, "first_commit": "2024-03-15 10:28:52", "latest_commit": "2024-06-20 20:58:44", "languages": [ @@ -15994,7 +16386,7 @@ "project_name": "AnnotatedFKCCorpus", "stargazers_count": 17, "source": "GitHub", - "score": -0.28750188169300517, + "score": -0.2861365465734436, "first_commit": "2021-01-18 19:32:38", "latest_commit": "2023-12-18 14:27:29", "languages": [ @@ -16008,7 +16400,7 @@ "project_name": "ebe-dataset", "stargazers_count": 17, "source": "GitHub", - "score": -0.28750188169300517, + "score": -0.2861365465734436, "first_commit": "2020-10-14 08:15:37", "latest_commit": "2020-12-17 13:39:55", "languages": [], @@ -16020,7 +16412,7 @@ "project_name": "loanwords_gairaigo", "stargazers_count": 17, "source": "GitHub", - "score": -0.28750188169300517, + "score": -0.2861365465734436, "first_commit": "2019-10-21 16:49:45", "latest_commit": "2021-01-08 12:40:02", "languages": [ @@ -16034,7 +16426,7 @@ "project_name": "hurigana-speech-corpus-aozora", "stargazers_count": 17, "source": "GitHub", - "score": -0.28750188169300517, + "score": -0.2861365465734436, "first_commit": "2024-01-16 11:30:12", "latest_commit": "2024-01-31 16:04:24", "languages": [], @@ -16046,7 +16438,7 @@ "project_name": "JASS", "stargazers_count": 16, "source": "GitHub", - "score": -0.290433423705603, + "score": -0.2890765671347133, "first_commit": "2020-02-19 11:19:42", "latest_commit": "2022-01-25 15:24:53", "languages": [], @@ -16058,7 +16450,7 @@ "project_name": "ginza-transformers", "stargazers_count": 16, "source": "GitHub", - "score": -0.290433423705603, + "score": -0.2890765671347133, "first_commit": "2021-06-23 17:42:12", "latest_commit": "2022-08-09 18:19:33", "languages": [ @@ -16072,7 +16464,7 @@ "project_name": "MedNER-J", "stargazers_count": 16, "source": "GitHub", - "score": -0.290433423705603, + "score": -0.2890765671347133, "first_commit": "2020-07-28 18:27:41", "latest_commit": "2022-05-17 20:01:05", "languages": [ @@ -16086,7 +16478,7 @@ "project_name": "AIO2_DPR_baseline", "stargazers_count": 16, "source": "GitHub", - "score": -0.290433423705603, + "score": -0.2890765671347133, "first_commit": "2021-09-13 16:33:09", "latest_commit": "2022-01-08 23:15:11", "languages": [ @@ -16100,7 +16492,7 @@ "project_name": "unsupervised-pos-tagging", "stargazers_count": 16, "source": "GitHub", - "score": -0.290433423705603, + "score": -0.2890765671347133, "first_commit": "2017-01-07 09:24:36", "latest_commit": "2017-10-11 23:23:04", "languages": [ @@ -16115,7 +16507,7 @@ "project_name": "furigana4epub", "stargazers_count": 16, "source": "GitHub", - "score": -0.290433423705603, + "score": -0.2890765671347133, "first_commit": "2021-08-29 20:14:15", "latest_commit": "2021-09-11 14:03:11", "languages": [ @@ -16129,7 +16521,7 @@ "project_name": "Laboro-DistilBERT-Japanese", "stargazers_count": 16, "source": "GitHub", - "score": -0.290433423705603, + "score": -0.2890765671347133, "first_commit": "2020-11-30 16:10:16", "latest_commit": "2020-12-17 15:26:01", "languages": [ @@ -16144,7 +16536,7 @@ "project_name": "character_chat", "stargazers_count": 16, "source": "GitHub", - "score": -0.290433423705603, + "score": -0.2890765671347133, "first_commit": "2023-03-19 03:36:06", "latest_commit": "2023-06-03 23:30:23", "languages": [ @@ -16158,7 +16550,7 @@ "project_name": "TEDxJP-10K", "stargazers_count": 16, "source": "GitHub", - "score": -0.290433423705603, + "score": -0.2890765671347133, "first_commit": "2021-01-14 13:14:28", "latest_commit": "2021-01-14 15:33:14", "languages": [ @@ -16172,7 +16564,7 @@ "project_name": "japanese-family-names", "stargazers_count": 16, "source": "GitHub", - "score": -0.290433423705603, + "score": -0.2890765671347133, "first_commit": "2017-06-08 18:00:02", "latest_commit": "2017-06-09 01:50:19", "languages": [ @@ -16186,7 +16578,7 @@ "project_name": "SuPar-UniDic", "stargazers_count": 15, "source": "GitHub", - "score": -0.29336496571820075, + "score": -0.292016587695983, "first_commit": "2021-02-21 09:42:27", "latest_commit": "2024-06-28 15:56:24", "languages": [ @@ -16201,7 +16593,7 @@ "project_name": "furiganapad", "stargazers_count": 15, "source": "GitHub", - "score": -0.29336496571820075, + "score": -0.292016587695983, "first_commit": "2019-05-14 02:56:41", "latest_commit": "2024-05-23 04:55:05", "languages": [ @@ -16215,7 +16607,7 @@ "project_name": "japanese_llm_simple_webui", "stargazers_count": 15, "source": "GitHub", - "score": -0.29336496571820075, + "score": -0.292016587695983, "first_commit": "2023-06-04 23:06:13", "latest_commit": "2024-05-12 22:10:56", "languages": [ @@ -16229,7 +16621,7 @@ "project_name": "gpt4-autoeval", "stargazers_count": 15, "source": "GitHub", - "score": -0.29336496571820075, + "score": -0.292016587695983, "first_commit": "2023-12-18 13:38:36", "latest_commit": "2024-06-06 13:50:35", "languages": [ @@ -16245,7 +16637,7 @@ "project_name": "llm-translator", "stargazers_count": 15, "source": "GitHub", - "score": -0.29336496571820075, + "score": -0.292016587695983, "first_commit": "2023-12-31 00:47:57", "latest_commit": "2023-12-31 00:53:57", "languages": [ @@ -16259,7 +16651,7 @@ "project_name": "kana2ipa", "stargazers_count": 15, "source": "GitHub", - "score": -0.29336496571820075, + "score": -0.292016587695983, "first_commit": "2019-12-23 00:07:17", "latest_commit": "2020-10-25 04:42:14", "languages": [ @@ -16273,7 +16665,7 @@ "project_name": "hololive-dictionary", "stargazers_count": 15, "source": "GitHub", - "score": -0.29336496571820075, + "score": -0.292016587695983, "first_commit": "2021-06-13 09:49:48", "latest_commit": "2024-05-02 16:25:29", "languages": [ @@ -16287,7 +16679,7 @@ "project_name": "pixiv-yomitan", "stargazers_count": 15, "source": "GitHub", - "score": -0.29336496571820075, + "score": -0.292016587695983, "first_commit": "2024-02-09 19:59:45", "latest_commit": "2024-07-23 22:00:16", "languages": [ @@ -16301,7 +16693,7 @@ "project_name": "Laboro-ParaCorpus", "stargazers_count": 15, "source": "GitHub", - "score": -0.29336496571820075, + "score": -0.292016587695983, "first_commit": "2021-09-29 18:37:50", "latest_commit": "2021-11-09 10:18:54", "languages": [ @@ -16316,7 +16708,7 @@ "project_name": "ginza-examples", "stargazers_count": 15, "source": "GitHub", - "score": -0.29336496571820075, + "score": -0.292016587695983, "first_commit": "2020-08-25 02:24:01", "latest_commit": "2021-01-29 00:04:15", "languages": [ @@ -16330,7 +16722,7 @@ "project_name": "japanese-sentence-breaker", "stargazers_count": 14, "source": "GitHub", - "score": -0.2962965077307985, + "score": -0.29495660825725273, "first_commit": "2021-02-28 21:40:27", "latest_commit": "2021-02-28 22:47:20", "languages": [ @@ -16344,7 +16736,7 @@ "project_name": "jsc", "stargazers_count": 14, "source": "GitHub", - "score": -0.2962965077307985, + "score": -0.29495660825725273, "first_commit": "2012-08-23 16:39:41", "latest_commit": "2012-12-19 18:36:09", "languages": [ @@ -16358,7 +16750,7 @@ "project_name": "aMLP-japanese", "stargazers_count": 14, "source": "GitHub", - "score": -0.2962965077307985, + "score": -0.29495660825725273, "first_commit": "2021-11-13 16:17:10", "latest_commit": "2022-05-10 14:16:55", "languages": [ @@ -16372,7 +16764,7 @@ "project_name": "openai-chatfriend", "stargazers_count": 14, "source": "GitHub", - "score": -0.2962965077307985, + "score": -0.29495660825725273, "first_commit": "2023-01-17 15:19:27", "latest_commit": "2023-04-03 10:19:35", "languages": [ @@ -16387,7 +16779,7 @@ "project_name": "mozcdic-ut-place-names", "stargazers_count": 14, "source": "GitHub", - "score": -0.2962965077307985, + "score": -0.29495660825725273, "first_commit": "2023-01-15 18:01:48", "latest_commit": "2024-08-07 03:05:50", "languages": [ @@ -16401,7 +16793,7 @@ "project_name": "oasst1-89k-ja", "stargazers_count": 14, "source": "GitHub", - "score": -0.2962965077307985, + "score": -0.29495660825725273, "first_commit": "2023-05-07 05:27:23", "latest_commit": "2023-11-20 00:23:10", "languages": [ @@ -16415,7 +16807,7 @@ "project_name": "dango", "stargazers_count": 13, "source": "GitHub", - "score": -0.29922804974339634, + "score": -0.2978966288185224, "first_commit": "2021-06-20 13:18:31", "latest_commit": "2021-11-21 19:41:04", "languages": [ @@ -16429,7 +16821,7 @@ "project_name": "PheMT", "stargazers_count": 13, "source": "GitHub", - "score": -0.29922804974339634, + "score": -0.2978966288185224, "first_commit": "2020-10-27 17:05:01", "latest_commit": "2021-02-18 14:05:26", "languages": [ @@ -16443,7 +16835,7 @@ "project_name": "entitypedia", "stargazers_count": 13, "source": "GitHub", - "score": -0.29922804974339634, + "score": -0.2978966288185224, "first_commit": "2017-11-08 13:54:21", "latest_commit": "2018-12-10 12:53:58", "languages": [ @@ -16459,7 +16851,7 @@ "project_name": "gector-ja", "stargazers_count": 13, "source": "GitHub", - "score": -0.29922804974339634, + "score": -0.2978966288185224, "first_commit": "2021-05-11 04:51:42", "latest_commit": "2021-07-16 18:55:03", "languages": [ @@ -16473,7 +16865,7 @@ "project_name": "negima", "stargazers_count": 13, "source": "GitHub", - "score": -0.29922804974339634, + "score": -0.2978966288185224, "first_commit": "2018-06-27 01:49:31", "latest_commit": "2018-08-20 12:31:43", "languages": [ @@ -16487,7 +16879,7 @@ "project_name": "clip-japanese", "stargazers_count": 13, "source": "GitHub", - "score": -0.29922804974339634, + "score": -0.2978966288185224, "first_commit": "2022-02-24 20:42:33", "latest_commit": "2023-03-12 18:43:17", "languages": [ @@ -16501,7 +16893,7 @@ "project_name": "fcitx5-hazkey", "stargazers_count": 13, "source": "GitHub", - "score": -0.29922804974339634, + "score": -0.2978966288185224, "first_commit": "2024-05-21 22:15:24", "latest_commit": "2024-08-01 12:39:04", "languages": [ @@ -16516,7 +16908,7 @@ "project_name": "ndlngramdata", "stargazers_count": 13, "source": "GitHub", - "score": -0.29922804974339634, + "score": -0.2978966288185224, "first_commit": "2022-12-06 10:20:12", "latest_commit": "2023-01-10 10:38:37", "languages": [], @@ -16528,7 +16920,7 @@ "project_name": "alphabet2kana", "stargazers_count": 12, "source": "GitHub", - "score": -0.3021595917559941, + "score": -0.3008366493797921, "first_commit": "2021-03-21 12:29:41", "latest_commit": "2024-08-10 11:10:20", "languages": [ @@ -16542,7 +16934,7 @@ "project_name": "allennlp-shiba-model", "stargazers_count": 12, "source": "GitHub", - "score": -0.3021595917559941, + "score": -0.3008366493797921, "first_commit": "2021-06-26 18:37:25", "latest_commit": "2021-06-27 00:42:45", "languages": [ @@ -16556,7 +16948,7 @@ "project_name": "NTM", "stargazers_count": 12, "source": "GitHub", - "score": -0.3021595917559941, + "score": -0.3008366493797921, "first_commit": "2019-07-24 20:14:25", "latest_commit": "2019-07-24 22:26:58", "languages": [ @@ -16570,7 +16962,7 @@ "project_name": "ClipCap-for-Japanese", "stargazers_count": 12, "source": "GitHub", - "score": -0.3021595917559941, + "score": -0.3008366493797921, "first_commit": "2022-10-05 00:44:54", "latest_commit": "2022-10-05 02:08:58", "languages": [ @@ -16584,7 +16976,7 @@ "project_name": "easynovelassistant", "stargazers_count": 12, "source": "GitHub", - "score": -0.3021595917559941, + "score": -0.3008366493797921, "first_commit": "2024-04-22 15:59:35", "latest_commit": "2024-07-05 17:29:36", "languages": [ @@ -16598,7 +16990,7 @@ "project_name": "deep-question-generation", "stargazers_count": 12, "source": "GitHub", - "score": -0.3021595917559941, + "score": -0.3008366493797921, "first_commit": "2021-03-07 17:01:23", "latest_commit": "2023-03-12 18:47:52", "languages": [ @@ -16612,7 +17004,7 @@ "project_name": "kanaria", "stargazers_count": 12, "source": "GitHub", - "score": -0.3021595917559941, + "score": -0.3008366493797921, "first_commit": "2019-01-07 22:16:32", "latest_commit": "2024-06-28 09:48:18", "languages": [ @@ -16628,7 +17020,7 @@ "project_name": "medbertjp", "stargazers_count": 12, "source": "GitHub", - "score": -0.3021595917559941, + "score": -0.3008366493797921, "first_commit": "2020-10-23 03:07:15", "latest_commit": "2020-11-22 08:37:27", "languages": [ @@ -16643,7 +17035,7 @@ "project_name": "albert-japanese-tinysegmenter", "stargazers_count": 12, "source": "GitHub", - "score": -0.3021595917559941, + "score": -0.3008366493797921, "first_commit": "2023-06-04 15:21:32", "latest_commit": "2023-09-26 23:07:55", "languages": [ @@ -16657,7 +17049,7 @@ "project_name": "easylightchatassistant", "stargazers_count": 12, "source": "GitHub", - "score": -0.3021595917559941, + "score": -0.3008366493797921, "first_commit": "2024-04-06 17:40:16", "latest_commit": "2024-04-24 00:49:12", "languages": [], @@ -16669,7 +17061,7 @@ "project_name": "Ayashiy-Nipongo-Dic", "stargazers_count": 12, "source": "GitHub", - "score": -0.3021595917559941, + "score": -0.3008366493797921, "first_commit": "2021-12-14 11:50:25", "latest_commit": "2024-05-01 15:23:24", "languages": [], @@ -16681,7 +17073,7 @@ "project_name": "Web-Crawled-Corpus-for-Japanese-Chinese-NMT", "stargazers_count": 12, "source": "GitHub", - "score": -0.3021595917559941, + "score": -0.3008366493797921, "first_commit": "2021-11-12 23:19:26", "latest_commit": "2023-10-01 03:13:18", "languages": [], @@ -16693,7 +17085,7 @@ "project_name": "CourseraParallelCorpusMining", "stargazers_count": 12, "source": "GitHub", - "score": -0.3021595917559941, + "score": -0.3008366493797921, "first_commit": "2020-01-09 18:09:50", "latest_commit": "2022-06-14 14:18:29", "languages": [ @@ -16708,7 +17100,7 @@ "project_name": "honkoku-data", "stargazers_count": 12, "source": "GitHub", - "score": -0.3021595917559941, + "score": -0.3008366493797921, "first_commit": "2020-02-23 16:47:55", "latest_commit": "2024-06-14 17:43:19", "languages": [], @@ -16720,7 +17112,7 @@ "project_name": "commonsense-moral-ja", "stargazers_count": 12, "source": "GitHub", - "score": -0.3021595917559941, + "score": -0.3008366493797921, "first_commit": "2022-12-29 13:18:05", "latest_commit": "2023-12-18 11:41:00", "languages": [ @@ -16734,7 +17126,7 @@ "project_name": "text-cleaning", "stargazers_count": 11, "source": "GitHub", - "score": -0.3050911337685919, + "score": -0.30377666994106184, "first_commit": "2020-02-10 15:31:27", "latest_commit": "2022-11-21 10:21:56", "languages": [ @@ -16748,7 +17140,7 @@ "project_name": "VISA", "stargazers_count": 11, "source": "GitHub", - "score": -0.3050911337685919, + "score": -0.30377666994106184, "first_commit": "2022-03-25 17:15:42", "latest_commit": "2022-10-17 10:34:12", "languages": [], @@ -16760,7 +17152,7 @@ "project_name": "bert-japanese-ner-finetuning", "stargazers_count": 11, "source": "GitHub", - "score": -0.3050911337685919, + "score": -0.30377666994106184, "first_commit": "2021-11-14 22:57:16", "latest_commit": "2022-06-19 16:24:15", "languages": [ @@ -16775,7 +17167,7 @@ "project_name": "evaluate_japanese_w2v", "stargazers_count": 11, "source": "GitHub", - "score": -0.3050911337685919, + "score": -0.30377666994106184, "first_commit": "2020-02-07 08:02:49", "latest_commit": "2023-11-03 21:09:04", "languages": [ @@ -16789,7 +17181,7 @@ "project_name": "prefix-tuning-gpt", "stargazers_count": 11, "source": "GitHub", - "score": -0.3050911337685919, + "score": -0.30377666994106184, "first_commit": "2022-09-05 16:56:23", "latest_commit": "2023-03-22 14:13:22", "languages": [ @@ -16803,7 +17195,7 @@ "project_name": "asa-python", "stargazers_count": 11, "source": "GitHub", - "score": -0.3050911337685919, + "score": -0.30377666994106184, "first_commit": "2017-09-13 22:02:47", "latest_commit": "2019-02-16 23:52:13", "languages": [ @@ -16817,7 +17209,7 @@ "project_name": "jel", "stargazers_count": 11, "source": "GitHub", - "score": -0.3050911337685919, + "score": -0.30377666994106184, "first_commit": "2021-05-01 15:53:49", "latest_commit": "2021-07-25 13:01:46", "languages": [ @@ -16831,7 +17223,7 @@ "project_name": "python-npycrf", "stargazers_count": 11, "source": "GitHub", - "score": -0.3050911337685919, + "score": -0.30377666994106184, "first_commit": "2017-07-01 18:00:52", "latest_commit": "2018-03-23 00:04:16", "languages": [ @@ -16846,7 +17238,7 @@ "project_name": "aozora_classification", "stargazers_count": 11, "source": "GitHub", - "score": -0.3050911337685919, + "score": -0.30377666994106184, "first_commit": "2017-03-05 12:30:50", "latest_commit": "2017-09-03 12:01:40", "languages": [ @@ -16861,7 +17253,7 @@ "project_name": "ja-law-parser", "stargazers_count": 11, "source": "GitHub", - "score": -0.3050911337685919, + "score": -0.30377666994106184, "first_commit": "2023-11-26 19:38:36", "latest_commit": "2024-01-14 19:59:45", "languages": [ @@ -16875,7 +17267,7 @@ "project_name": "jawiki_word_vector_updater", "stargazers_count": 11, "source": "GitHub", - "score": -0.3050911337685919, + "score": -0.30377666994106184, "first_commit": "2019-02-13 16:18:58", "latest_commit": "2020-05-07 02:25:19", "languages": [], @@ -16887,7 +17279,7 @@ "project_name": "sbert-ja", "stargazers_count": 11, "source": "GitHub", - "score": -0.3050911337685919, + "score": -0.30377666994106184, "first_commit": "2021-07-31 01:11:17", "latest_commit": "2021-08-08 15:47:30", "languages": [ @@ -16901,7 +17293,7 @@ "project_name": "kyoto-reader", "stargazers_count": 10, "source": "GitHub", - "score": -0.3080226757811897, + "score": -0.3067166905023315, "first_commit": "2019-11-15 20:46:54", "latest_commit": "2024-06-26 12:45:20", "languages": [ @@ -16915,7 +17307,7 @@ "project_name": "zunda-python", "stargazers_count": 10, "source": "GitHub", - "score": -0.3080226757811897, + "score": -0.3067166905023315, "first_commit": "2019-02-24 01:08:40", "latest_commit": "2019-11-30 18:44:15", "languages": [ @@ -16929,7 +17321,7 @@ "project_name": "wikipedia-passages-jawiki-embeddings-utils", "stargazers_count": 10, "source": "GitHub", - "score": -0.3080226757811897, + "score": -0.3067166905023315, "first_commit": "2023-11-14 11:34:23", "latest_commit": "2024-03-29 08:18:44", "languages": [ @@ -16944,7 +17336,7 @@ "project_name": "jisho", "stargazers_count": 10, "source": "GitHub", - "score": -0.3080226757811897, + "score": -0.3067166905023315, "first_commit": null, "latest_commit": null, "languages": [], @@ -16956,7 +17348,7 @@ "project_name": "j-liwc2015", "stargazers_count": 10, "source": "GitHub", - "score": -0.3080226757811897, + "score": -0.3067166905023315, "first_commit": "2021-09-04 09:11:35", "latest_commit": "2022-11-15 15:37:27", "languages": [], @@ -16968,7 +17360,7 @@ "project_name": "huriganacorpus-aozora", "stargazers_count": 10, "source": "GitHub", - "score": -0.3080226757811897, + "score": -0.3067166905023315, "first_commit": "2021-08-31 16:37:20", "latest_commit": "2024-01-17 18:05:54", "languages": [], @@ -16980,7 +17372,7 @@ "project_name": "python-nlp-book", "stargazers_count": 10, "source": "GitHub", - "score": -0.3080226757811897, + "score": -0.3067166905023315, "first_commit": "2023-01-28 18:34:33", "latest_commit": "2023-05-07 23:55:27", "languages": [ @@ -16994,7 +17386,7 @@ "project_name": "Jusho", "stargazers_count": 9, "source": "GitHub", - "score": -0.31095421779378746, + "score": -0.3096567110636012, "first_commit": "2020-11-12 03:39:08", "latest_commit": "2024-06-04 16:03:08", "languages": [ @@ -17008,7 +17400,7 @@ "project_name": "ja-senter-benchmark", "stargazers_count": 9, "source": "GitHub", - "score": -0.31095421779378746, + "score": -0.3096567110636012, "first_commit": "2023-02-10 12:58:42", "latest_commit": "2023-02-27 17:58:52", "languages": [ @@ -17022,7 +17414,7 @@ "project_name": "japanese_text_classification", "stargazers_count": 9, "source": "GitHub", - "score": -0.31095421779378746, + "score": -0.3096567110636012, "first_commit": "2019-07-01 18:33:17", "latest_commit": "2020-01-15 19:12:53", "languages": [ @@ -17037,7 +17429,7 @@ "project_name": "pyknp-eventgraph", "stargazers_count": 9, "source": "GitHub", - "score": -0.31095421779378746, + "score": -0.3096567110636012, "first_commit": "2019-11-21 21:46:46", "latest_commit": "2022-09-26 12:21:44", "languages": [ @@ -17051,7 +17443,7 @@ "project_name": "japanese_summarizer", "stargazers_count": 9, "source": "GitHub", - "score": -0.31095421779378746, + "score": -0.3096567110636012, "first_commit": "2020-08-18 20:44:35", "latest_commit": "2022-08-01 20:28:21", "languages": [ @@ -17065,7 +17457,7 @@ "project_name": "WordCloud-Japanese", "stargazers_count": 9, "source": "GitHub", - "score": -0.31095421779378746, + "score": -0.3096567110636012, "first_commit": "2019-05-11 13:59:53", "latest_commit": "2020-01-02 06:45:49", "languages": [ @@ -17079,7 +17471,7 @@ "project_name": "snark", "stargazers_count": 9, "source": "GitHub", - "score": -0.31095421779378746, + "score": -0.3096567110636012, "first_commit": "2018-12-22 18:37:03", "latest_commit": "2020-03-11 22:01:51", "languages": [ @@ -17093,7 +17485,7 @@ "project_name": "PyKatsuyou", "stargazers_count": 9, "source": "GitHub", - "score": -0.31095421779378746, + "score": -0.3096567110636012, "first_commit": "2022-01-01 01:25:25", "latest_commit": "2023-09-04 17:26:36", "languages": [ @@ -17107,7 +17499,7 @@ "project_name": "JaSPICE", "stargazers_count": 9, "source": "GitHub", - "score": -0.31095421779378746, + "score": -0.3096567110636012, "first_commit": "2023-03-01 19:14:54", "latest_commit": "2023-11-08 21:16:53", "languages": [ @@ -17121,7 +17513,7 @@ "project_name": "bertjsc", "stargazers_count": 9, "source": "GitHub", - "score": -0.31095421779378746, + "score": -0.3096567110636012, "first_commit": "2023-03-16 11:05:59", "latest_commit": "2024-08-03 12:15:17", "languages": [ @@ -17136,7 +17528,7 @@ "project_name": "awabi", "stargazers_count": 9, "source": "GitHub", - "score": -0.31095421779378746, + "score": -0.3096567110636012, "first_commit": "2020-03-13 08:08:26", "latest_commit": "2024-07-01 16:35:36", "languages": [ @@ -17150,7 +17542,7 @@ "project_name": "dependency-based-japanese-word-embeddings", "stargazers_count": 9, "source": "GitHub", - "score": -0.31095421779378746, + "score": -0.3096567110636012, "first_commit": "2019-07-31 15:42:14", "latest_commit": "2019-08-14 11:39:35", "languages": [], @@ -17162,7 +17554,7 @@ "project_name": "AMI-Meeting-Parallel-Corpus", "stargazers_count": 9, "source": "GitHub", - "score": -0.31095421779378746, + "score": -0.3096567110636012, "first_commit": "2020-12-11 14:22:19", "latest_commit": "2020-12-11 16:41:42", "languages": [], @@ -17174,7 +17566,7 @@ "project_name": "huggingface-datasets_JGLUE", "stargazers_count": 9, "source": "GitHub", - "score": -0.31095421779378746, + "score": -0.3096567110636012, "first_commit": "2023-02-25 13:33:13", "latest_commit": "2024-05-21 11:23:51", "languages": [ @@ -17188,7 +17580,7 @@ "project_name": "meconaudio", "stargazers_count": 9, "source": "GitHub", - "score": -0.31095421779378746, + "score": -0.3096567110636012, "first_commit": "2023-04-12 13:43:26", "latest_commit": "2023-10-26 08:40:27", "languages": [], @@ -17200,7 +17592,7 @@ "project_name": "GEC-Info-ja", "stargazers_count": 9, "source": "GitHub", - "score": -0.31095421779378746, + "score": -0.3096567110636012, "first_commit": "2022-07-02 01:07:27", "latest_commit": "2024-03-27 01:15:21", "languages": [], @@ -17212,7 +17604,7 @@ "project_name": "jagger-python", "stargazers_count": 8, "source": "GitHub", - "score": -0.3138857598063853, + "score": -0.31259673162487095, "first_commit": "2023-12-27 22:09:07", "latest_commit": "2024-03-12 02:15:59", "languages": [ @@ -17226,7 +17618,7 @@ "project_name": "text2phoneme", "stargazers_count": 8, "source": "GitHub", - "score": -0.3138857598063853, + "score": -0.31259673162487095, "first_commit": "2023-04-25 22:53:08", "latest_commit": "2023-05-17 00:44:01", "languages": [ @@ -17240,7 +17632,7 @@ "project_name": "DNorm-J", "stargazers_count": 8, "source": "GitHub", - "score": -0.3138857598063853, + "score": -0.31259673162487095, "first_commit": "2020-05-07 13:47:43", "latest_commit": "2022-06-30 12:09:11", "languages": [ @@ -17254,7 +17646,7 @@ "project_name": "JaMIE", "stargazers_count": 8, "source": "GitHub", - "score": -0.3138857598063853, + "score": -0.31259673162487095, "first_commit": "2019-10-09 11:44:21", "latest_commit": "2023-05-18 05:19:18", "languages": [ @@ -17268,7 +17660,7 @@ "project_name": "BLIP2-Japanese", "stargazers_count": 8, "source": "GitHub", - "score": -0.3138857598063853, + "score": -0.31259673162487095, "first_commit": "2023-05-31 22:24:24", "latest_commit": "2024-01-16 08:54:50", "languages": [ @@ -17283,7 +17675,7 @@ "project_name": "shisa-v2", "stargazers_count": 8, "source": "GitHub", - "score": -0.3138857598063853, + "score": -0.31259673162487095, "first_commit": "2024-03-29 15:12:36", "latest_commit": "2024-07-30 00:26:10", "languages": [ @@ -17297,7 +17689,7 @@ "project_name": "mecab-ipadic-seed", "stargazers_count": 8, "source": "GitHub", - "score": -0.3138857598063853, + "score": -0.31259673162487095, "first_commit": "2016-07-18 01:26:14", "latest_commit": "2016-07-30 19:09:57", "languages": [ @@ -17311,7 +17703,7 @@ "project_name": "AcademicRoBERTa", "stargazers_count": 8, "source": "GitHub", - "score": -0.3138857598063853, + "score": -0.31259673162487095, "first_commit": "2022-09-05 15:58:57", "latest_commit": "2023-05-16 13:48:22", "languages": [ @@ -17325,7 +17717,7 @@ "project_name": "mecab-mozcdic", "stargazers_count": 8, "source": "GitHub", - "score": -0.3138857598063853, + "score": -0.31259673162487095, "first_commit": "2017-07-21 20:37:42", "latest_commit": "2018-01-12 16:07:57", "languages": [], @@ -17337,7 +17729,7 @@ "project_name": "anthy", "stargazers_count": 8, "source": "GitHub", - "score": -0.3138857598063853, + "score": -0.31259673162487095, "first_commit": "2010-05-14 14:19:43", "latest_commit": "2023-02-25 21:37:47", "languages": [ @@ -17352,7 +17744,7 @@ "project_name": "jcms", "stargazers_count": 8, "source": "GitHub", - "score": -0.3138857598063853, + "score": -0.31259673162487095, "first_commit": "2022-11-07 15:44:38", "latest_commit": "2022-11-07 16:40:03", "languages": [ @@ -17366,7 +17758,7 @@ "project_name": "ndl-minhon-ocrdataset", "stargazers_count": 8, "source": "GitHub", - "score": -0.3138857598063853, + "score": -0.31259673162487095, "first_commit": "2023-01-19 15:22:00", "latest_commit": "2024-02-07 14:16:11", "languages": [ @@ -17380,7 +17772,7 @@ "project_name": "WLSP-familiarity", "stargazers_count": 8, "source": "GitHub", - "score": -0.3138857598063853, + "score": -0.31259673162487095, "first_commit": "2019-03-13 10:26:42", "latest_commit": "2024-06-30 15:05:18", "languages": [], @@ -17392,7 +17784,7 @@ "project_name": "jamorasep", "stargazers_count": 7, "source": "GitHub", - "score": -0.31681730181898304, + "score": -0.31553675218614063, "first_commit": "2023-03-08 22:54:34", "latest_commit": "2023-09-09 01:14:14", "languages": [ @@ -17406,7 +17798,7 @@ "project_name": "text_recognition", "stargazers_count": 7, "source": "GitHub", - "score": -0.31681730181898304, + "score": -0.31553675218614063, "first_commit": "2022-03-30 13:32:26", "latest_commit": "2023-07-10 18:03:39", "languages": [ @@ -17420,7 +17812,7 @@ "project_name": "kantan", "stargazers_count": 7, "source": "GitHub", - "score": -0.31681730181898304, + "score": -0.31553675218614063, "first_commit": "2015-07-15 12:45:17", "latest_commit": "2022-07-20 20:10:04", "languages": [ @@ -17434,7 +17826,7 @@ "project_name": "aozora-corpus-generator", "stargazers_count": 7, "source": "GitHub", - "score": -0.31681730181898304, + "score": -0.31553675218614063, "first_commit": "2017-10-09 16:11:26", "latest_commit": "2022-04-04 13:15:59", "languages": [ @@ -17448,7 +17840,7 @@ "project_name": "AugLy-jp", "stargazers_count": 7, "source": "GitHub", - "score": -0.31681730181898304, + "score": -0.31553675218614063, "first_commit": "2021-06-13 18:48:45", "latest_commit": "2021-09-30 13:16:24", "languages": [ @@ -17463,7 +17855,7 @@ "project_name": "julius4seg", "stargazers_count": 7, "source": "GitHub", - "score": -0.31681730181898304, + "score": -0.31553675218614063, "first_commit": "2018-02-20 23:19:39", "latest_commit": "2021-08-22 18:57:51", "languages": [ @@ -17477,7 +17869,7 @@ "project_name": "sentiment_ja_js", "stargazers_count": 7, "source": "GitHub", - "score": -0.31681730181898304, + "score": -0.31553675218614063, "first_commit": "2021-12-08 22:48:44", "latest_commit": "2021-12-10 00:56:29", "languages": [ @@ -17491,7 +17883,7 @@ "project_name": "manbyo-sudachi", "stargazers_count": 7, "source": "GitHub", - "score": -0.31681730181898304, + "score": -0.31553675218614063, "first_commit": "2021-04-05 15:59:36", "latest_commit": "2021-04-06 18:04:00", "languages": [ @@ -17505,7 +17897,7 @@ "project_name": "aws_dic_for_google_ime", "stargazers_count": 7, "source": "GitHub", - "score": -0.31681730181898304, + "score": -0.31553675218614063, "first_commit": "2019-11-24 03:47:55", "latest_commit": "2019-11-30 09:28:33", "languages": [ @@ -17520,7 +17912,7 @@ "project_name": "hirakanadic", "stargazers_count": 7, "source": "GitHub", - "score": -0.31681730181898304, + "score": -0.31553675218614063, "first_commit": "2021-06-22 21:38:13", "latest_commit": "2023-07-08 17:22:15", "languages": [ @@ -17534,7 +17926,7 @@ "project_name": "GazeVQA", "stargazers_count": 7, "source": "GitHub", - "score": -0.31681730181898304, + "score": -0.31553675218614063, "first_commit": "2024-02-22 06:53:00", "latest_commit": "2024-05-20 11:17:25", "languages": [], @@ -17546,7 +17938,7 @@ "project_name": "JapaneseNLI", "stargazers_count": 7, "source": "GitHub", - "score": -0.31681730181898304, + "score": -0.31553675218614063, "first_commit": "2020-03-10 22:43:24", "latest_commit": "2021-06-08 23:48:55", "languages": [ @@ -17560,7 +17952,7 @@ "project_name": "cabocha", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2011-07-29 04:08:14", "latest_commit": "2022-08-17 22:24:13", "languages": [ @@ -17579,7 +17971,7 @@ "project_name": "noyaki", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2021-05-23 18:41:17", "latest_commit": "2022-08-25 18:42:55", "languages": [ @@ -17593,7 +17985,7 @@ "project_name": "bert-ner-japanese", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2022-09-26 18:20:34", "latest_commit": "2022-09-26 21:44:38", "languages": [ @@ -17607,7 +17999,7 @@ "project_name": "jmlm_scoring", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2021-08-13 09:18:33", "latest_commit": "2022-02-20 22:39:25", "languages": [ @@ -17621,7 +18013,7 @@ "project_name": "swallow-evaluation", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2023-10-30 14:34:19", "latest_commit": "2024-07-13 21:29:54", "languages": [ @@ -17637,7 +18029,7 @@ "project_name": "showcase", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2018-06-26 13:19:53", "latest_commit": "2018-06-26 16:53:20", "languages": [ @@ -17651,7 +18043,7 @@ "project_name": "desuwa", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2021-04-20 16:37:43", "latest_commit": "2022-05-23 12:27:37", "languages": [ @@ -17665,7 +18057,7 @@ "project_name": "chirptext", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2014-12-01 20:39:06", "latest_commit": "2022-10-04 21:57:00", "languages": [ @@ -17679,7 +18071,7 @@ "project_name": "mixture-of-unigram-model", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2016-01-05 15:33:24", "latest_commit": "2017-06-16 13:33:57", "languages": [ @@ -17693,7 +18085,7 @@ "project_name": "mlm-scoring-transformers", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2022-10-03 14:27:09", "latest_commit": "2022-12-14 20:07:24", "languages": [ @@ -17707,7 +18099,7 @@ "project_name": "tra-fugu", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2023-02-28 21:41:49", "latest_commit": "2023-03-02 03:10:38", "languages": [ @@ -17721,7 +18113,7 @@ "project_name": "wikipedia-japanese-open-rag", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2023-12-28 07:55:40", "latest_commit": "2024-01-06 19:46:00", "languages": [ @@ -17735,7 +18127,7 @@ "project_name": "pydomino", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2024-05-27 10:52:07", "latest_commit": "2024-07-23 11:16:10", "languages": [ @@ -17751,7 +18143,7 @@ "project_name": "magpie-nemotron", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2024-07-05 21:07:54", "latest_commit": "2024-07-05 23:35:16", "languages": [ @@ -17765,7 +18157,7 @@ "project_name": "kana", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2022-06-28 22:39:35", "latest_commit": "2023-02-10 19:03:27", "languages": [], @@ -17777,7 +18169,7 @@ "project_name": "niinii", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2021-06-27 18:31:51", "latest_commit": "2024-08-11 11:54:57", "languages": [ @@ -17791,7 +18183,7 @@ "project_name": "AITuberDegikkoMirii", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2023-03-07 21:35:01", "latest_commit": "2023-03-18 06:59:43", "languages": [ @@ -17805,7 +18197,7 @@ "project_name": "Winograd-Schema-Challenge-Ja", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2019-01-25 19:14:29", "latest_commit": "2019-01-25 23:52:18", "languages": [ @@ -17819,7 +18211,7 @@ "project_name": "GeneralPolicySpeechOfPrimeMinisterOfJapan", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2014-10-28 00:56:59", "latest_commit": "2020-01-14 09:53:30", "languages": [], @@ -17831,7 +18223,7 @@ "project_name": "dcsg-ja", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2023-01-04 17:36:44", "latest_commit": "2023-03-10 17:29:26", "languages": [], @@ -17843,7 +18235,7 @@ "project_name": "ramendb", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2018-03-24 21:21:59", "latest_commit": "2024-08-06 10:47:04", "languages": [ @@ -17857,7 +18249,7 @@ "project_name": "J-CRe3", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2024-03-04 01:40:27", "latest_commit": "2024-06-14 18:24:05", "languages": [], @@ -17869,7 +18261,7 @@ "project_name": "pdmocrdataset-part2", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2022-05-24 10:37:30", "latest_commit": "2024-06-26 16:10:28", "languages": [], @@ -17881,7 +18273,7 @@ "project_name": "nlpbook", "stargazers_count": 6, "source": "GitHub", - "score": -0.31974884383158086, + "score": -0.3184767727474103, "first_commit": "2024-05-16 08:44:03", "latest_commit": "2024-07-03 14:25:21", "languages": [], @@ -17893,7 +18285,7 @@ "project_name": "jptranstokenizer", "stargazers_count": 5, "source": "GitHub", - "score": -0.32268038584417863, + "score": -0.32141679330868006, "first_commit": "2022-08-24 19:35:03", "latest_commit": "2024-02-03 03:07:59", "languages": [ @@ -17907,7 +18299,7 @@ "project_name": "compare-ja-tokenizer", "stargazers_count": 5, "source": "GitHub", - "score": -0.32268038584417863, + "score": -0.32141679330868006, "first_commit": "2023-06-13 18:08:18", "latest_commit": "2023-06-16 10:18:55", "languages": [ @@ -17921,7 +18313,7 @@ "project_name": "jawiki-cleaner", "stargazers_count": 5, "source": "GitHub", - "score": -0.32268038584417863, + "score": -0.32141679330868006, "first_commit": "2021-02-21 20:04:59", "latest_commit": "2021-02-21 21:41:44", "languages": [ @@ -17935,7 +18327,7 @@ "project_name": "hidden-markov-model", "stargazers_count": 5, "source": "GitHub", - "score": -0.32268038584417863, + "score": -0.32141679330868006, "first_commit": "2016-10-17 14:33:56", "latest_commit": "2017-06-16 13:33:24", "languages": [ @@ -17949,7 +18341,7 @@ "project_name": "Ngram-language-model", "stargazers_count": 5, "source": "GitHub", - "score": -0.32268038584417863, + "score": -0.32141679330868006, "first_commit": "2017-12-05 14:45:11", "latest_commit": "2017-12-05 15:03:52", "languages": [ @@ -17963,7 +18355,7 @@ "project_name": "akaza", "stargazers_count": 5, "source": "GitHub", - "score": -0.32268038584417863, + "score": -0.32141679330868006, "first_commit": null, "latest_commit": null, "languages": [], @@ -17975,7 +18367,7 @@ "project_name": "elmo-japanese", "stargazers_count": 5, "source": "GitHub", - "score": -0.32268038584417863, + "score": -0.32141679330868006, "first_commit": "2019-10-01 12:16:29", "latest_commit": "2019-10-07 10:37:31", "languages": [ @@ -17989,7 +18381,7 @@ "project_name": "japagen", "stargazers_count": 5, "source": "GitHub", - "score": -0.32268038584417863, + "score": -0.32141679330868006, "first_commit": "2024-01-12 10:53:54", "latest_commit": "2024-08-09 17:41:21", "languages": [], @@ -18001,7 +18393,7 @@ "project_name": "giant_ja-en_parallel_corpus", "stargazers_count": 5, "source": "GitHub", - "score": -0.32268038584417863, + "score": -0.32141679330868006, "first_commit": "2019-08-04 12:01:19", "latest_commit": "2019-08-04 17:40:02", "languages": [ @@ -18015,7 +18407,7 @@ "project_name": "BPersona-chat", "stargazers_count": 5, "source": "GitHub", - "score": -0.32268038584417863, + "score": -0.32141679330868006, "first_commit": "2022-10-10 14:15:10", "latest_commit": "2023-01-12 17:39:24", "languages": [], @@ -18027,7 +18419,7 @@ "project_name": "ita-corpus-chuwa", "stargazers_count": 5, "source": "GitHub", - "score": -0.32268038584417863, + "score": -0.32141679330868006, "first_commit": "2021-07-16 21:19:53", "latest_commit": "2021-08-25 12:22:06", "languages": [ @@ -18041,7 +18433,7 @@ "project_name": "ProSub", "stargazers_count": 5, "source": "GitHub", - "score": -0.32268038584417863, + "score": -0.32141679330868006, "first_commit": "2021-09-12 18:55:13", "latest_commit": "2024-06-02 19:06:13", "languages": [ @@ -18055,7 +18447,7 @@ "project_name": "allennlp-NER-ja", "stargazers_count": 5, "source": "GitHub", - "score": -0.32268038584417863, + "score": -0.32141679330868006, "first_commit": "2022-05-05 10:28:23", "latest_commit": "2022-05-10 00:52:35", "languages": [ @@ -18069,7 +18461,7 @@ "project_name": "chariot-PyTorch-Japanese-text-classification", "stargazers_count": 5, "source": "GitHub", - "score": -0.32268038584417863, + "score": -0.32141679330868006, "first_commit": "2019-03-02 15:04:41", "latest_commit": "2019-03-19 02:51:30", "languages": [ @@ -18083,7 +18475,7 @@ "project_name": "hasami", "stargazers_count": 4, "source": "GitHub", - "score": -0.3256119278567764, + "score": -0.32435681386994974, "first_commit": "2020-12-30 21:32:13", "latest_commit": "2021-02-21 14:39:11", "languages": [ @@ -18097,7 +18489,7 @@ "project_name": "nagisa_bert", "stargazers_count": 4, "source": "GitHub", - "score": -0.3256119278567764, + "score": -0.32435681386994974, "first_commit": "2022-09-26 03:45:52", "latest_commit": "2023-12-23 16:14:09", "languages": [ @@ -18112,7 +18504,7 @@ "project_name": "toEmoji", "stargazers_count": 4, "source": "GitHub", - "score": -0.3256119278567764, + "score": -0.32435681386994974, "first_commit": "2018-02-25 14:52:07", "latest_commit": "2018-04-16 00:59:20", "languages": [ @@ -18126,7 +18518,7 @@ "project_name": "jinf", "stargazers_count": 4, "source": "GitHub", - "score": -0.3256119278567764, + "score": -0.32435681386994974, "first_commit": "2022-02-03 17:59:01", "latest_commit": "2022-12-27 10:28:22", "languages": [ @@ -18140,7 +18532,7 @@ "project_name": "japanese-nli-model", "stargazers_count": 4, "source": "GitHub", - "score": -0.3256119278567764, + "score": -0.32435681386994974, "first_commit": "2022-10-26 17:42:42", "latest_commit": "2022-10-26 17:42:42", "languages": [ @@ -18154,7 +18546,7 @@ "project_name": "go-kakasi", "stargazers_count": 4, "source": "GitHub", - "score": -0.3256119278567764, + "score": -0.32435681386994974, "first_commit": "2024-02-11 19:08:03", "latest_commit": "2024-03-03 18:23:56", "languages": [ @@ -18168,7 +18560,7 @@ "project_name": "neologdn-java", "stargazers_count": 4, "source": "GitHub", - "score": -0.3256119278567764, + "score": -0.32435681386994974, "first_commit": "2017-02-20 18:07:05", "latest_commit": "2021-10-11 22:35:59", "languages": [ @@ -18182,7 +18574,7 @@ "project_name": "jp-azureopenai-samples", "stargazers_count": 4, "source": "GitHub", - "score": -0.3256119278567764, + "score": -0.32435681386994974, "first_commit": "2023-06-21 21:27:33", "latest_commit": "2024-08-16 11:31:48", "languages": [ @@ -18198,7 +18590,7 @@ "project_name": "kanji-flashcard-app-gpt4", "stargazers_count": 4, "source": "GitHub", - "score": -0.3256119278567764, + "score": -0.32435681386994974, "first_commit": "2023-10-17 23:33:19", "latest_commit": "2023-10-17 23:41:17", "languages": [ @@ -18213,7 +18605,7 @@ "project_name": "google-vs-deepl-je", "stargazers_count": 4, "source": "GitHub", - "score": -0.3256119278567764, + "score": -0.32435681386994974, "first_commit": "2020-03-22 19:45:11", "latest_commit": "2020-03-22 23:27:00", "languages": [ @@ -18227,7 +18619,7 @@ "project_name": "jawikicorpus", "stargazers_count": 4, "source": "GitHub", - "score": -0.3256119278567764, + "score": -0.32435681386994974, "first_commit": "2018-04-05 01:07:48", "latest_commit": "2018-11-24 16:44:02", "languages": [], @@ -18239,7 +18631,7 @@ "project_name": "huggingface-datasets_wrime", "stargazers_count": 4, "source": "GitHub", - "score": -0.3256119278567764, + "score": -0.32435681386994974, "first_commit": "2023-01-12 10:43:54", "latest_commit": "2023-01-15 12:39:01", "languages": [ @@ -18253,7 +18645,7 @@ "project_name": "japanese-technical-dict", "stargazers_count": 4, "source": "GitHub", - "score": -0.3256119278567764, + "score": -0.32435681386994974, "first_commit": "2024-01-08 14:44:52", "latest_commit": "2024-06-18 00:54:03", "languages": [ @@ -18267,7 +18659,7 @@ "project_name": "mecab-text-cleaner", "stargazers_count": 3, "source": "GitHub", - "score": -0.3285434698693742, + "score": -0.32729683443121943, "first_commit": "2023-09-01 16:18:34", "latest_commit": "2024-03-29 00:06:20", "languages": [ @@ -18282,7 +18674,7 @@ "project_name": "python-habachen", "stargazers_count": 3, "source": "GitHub", - "score": -0.3285434698693742, + "score": -0.32729683443121943, "first_commit": "2023-10-04 07:40:00", "latest_commit": "2024-01-21 10:29:31", "languages": [ @@ -18299,7 +18691,7 @@ "project_name": "kuzukiri", "stargazers_count": 3, "source": "GitHub", - "score": -0.3285434698693742, + "score": -0.32729683443121943, "first_commit": "2021-11-20 00:05:51", "latest_commit": "2024-06-11 16:43:31", "languages": [ @@ -18315,7 +18707,7 @@ "project_name": "jrte-corpus_example", "stargazers_count": 3, "source": "GitHub", - "score": -0.3285434698693742, + "score": -0.32729683443121943, "first_commit": "2021-08-23 09:46:30", "latest_commit": "2021-11-19 13:11:47", "languages": [ @@ -18329,7 +18721,7 @@ "project_name": "mbart-finetuning", "stargazers_count": 3, "source": "GitHub", - "score": -0.3285434698693742, + "score": -0.32729683443121943, "first_commit": "2021-10-14 00:05:39", "latest_commit": "2021-10-14 00:16:10", "languages": [ @@ -18343,7 +18735,7 @@ "project_name": "tweet_extructor", "stargazers_count": 3, "source": "GitHub", - "score": -0.3285434698693742, + "score": -0.32729683443121943, "first_commit": "2018-06-20 16:23:11", "latest_commit": "2022-08-28 13:30:18", "languages": [ @@ -18357,7 +18749,7 @@ "project_name": "japanese_chatbot", "stargazers_count": 3, "source": "GitHub", - "score": -0.3285434698693742, + "score": -0.32729683443121943, "first_commit": null, "latest_commit": null, "languages": [], @@ -18369,7 +18761,7 @@ "project_name": "tokenizer-speed-bench", "stargazers_count": 3, "source": "GitHub", - "score": -0.3285434698693742, + "score": -0.32729683443121943, "first_commit": "2021-10-28 21:38:49", "latest_commit": "2023-03-01 14:07:29", "languages": [ @@ -18386,7 +18778,7 @@ "project_name": "listup_precedent", "stargazers_count": 3, "source": "GitHub", - "score": -0.3285434698693742, + "score": -0.32729683443121943, "first_commit": "2023-01-15 08:01:44", "latest_commit": "2024-05-11 22:30:27", "languages": [ @@ -18400,7 +18792,7 @@ "project_name": "juman-bin", "stargazers_count": 3, "source": "GitHub", - "score": -0.3285434698693742, + "score": -0.32729683443121943, "first_commit": "2017-05-11 13:18:41", "latest_commit": "2017-05-11 13:53:25", "languages": [ @@ -18414,7 +18806,7 @@ "project_name": "Japanese-Word-Of-The-Day", "stargazers_count": 3, "source": "GitHub", - "score": -0.3285434698693742, + "score": -0.32729683443121943, "first_commit": "2021-07-10 00:03:05", "latest_commit": "2021-08-11 03:03:38", "languages": [ @@ -18428,7 +18820,7 @@ "project_name": "jawikivec", "stargazers_count": 3, "source": "GitHub", - "score": -0.3285434698693742, + "score": -0.32729683443121943, "first_commit": "2018-06-04 01:22:54", "latest_commit": "2018-11-24 17:10:01", "languages": [], @@ -18440,7 +18832,7 @@ "project_name": "mh-dict-jp", "stargazers_count": 3, "source": "GitHub", - "score": -0.3285434698693742, + "score": -0.32729683443121943, "first_commit": "2023-04-27 20:01:36", "latest_commit": "2023-11-27 13:46:48", "languages": [ @@ -18454,7 +18846,7 @@ "project_name": "jesc_small", "stargazers_count": 3, "source": "GitHub", - "score": -0.3285434698693742, + "score": -0.32729683443121943, "first_commit": "2019-07-06 12:36:45", "latest_commit": "2019-07-06 12:49:24", "languages": [], @@ -18466,7 +18858,7 @@ "project_name": "japanese-corpus", "stargazers_count": 3, "source": "GitHub", - "score": -0.3285434698693742, + "score": -0.32729683443121943, "first_commit": "2018-08-19 04:18:55", "latest_commit": "2018-10-09 19:08:10", "languages": [], @@ -18478,7 +18870,7 @@ "project_name": "speechBSD", "stargazers_count": 3, "source": "GitHub", - "score": -0.3285434698693742, + "score": -0.32729683443121943, "first_commit": "2022-05-30 11:17:29", "latest_commit": "2024-02-07 22:15:37", "languages": [], @@ -18490,7 +18882,7 @@ "project_name": "anlp-jp-history", "stargazers_count": 3, "source": "GitHub", - "score": -0.3285434698693742, + "score": -0.32729683443121943, "first_commit": "2015-08-12 17:40:32", "latest_commit": "2024-04-05 19:33:15", "languages": [ @@ -18504,7 +18896,7 @@ "project_name": "handson-language-models", "stargazers_count": 3, "source": "GitHub", - "score": -0.3285434698693742, + "score": -0.32729683443121943, "first_commit": "2021-03-13 15:29:37", "latest_commit": "2021-03-18 19:33:34", "languages": [ @@ -18518,7 +18910,7 @@ "project_name": "jdepp-python", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2024-01-01 23:34:44", "latest_commit": "2024-02-14 22:09:31", "languages": [ @@ -18532,7 +18924,7 @@ "project_name": "wiredify", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2023-09-03 09:17:14", "latest_commit": "2023-12-19 01:01:46", "languages": [ @@ -18546,7 +18938,7 @@ "project_name": "utsuho", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2023-03-27 11:07:55", "latest_commit": "2023-11-20 08:53:43", "languages": [ @@ -18560,7 +18952,7 @@ "project_name": "Japanese-BERT-Sentiment-Analyzer", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2021-03-17 22:22:31", "latest_commit": "2021-04-20 00:41:29", "languages": [ @@ -18574,7 +18966,7 @@ "project_name": "ishi", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2019-12-21 17:24:25", "latest_commit": "2020-05-15 22:18:26", "languages": [ @@ -18588,7 +18980,7 @@ "project_name": "unihan-lm", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2020-09-14 16:41:10", "latest_commit": "2020-11-06 10:12:50", "languages": [ @@ -18602,7 +18994,7 @@ "project_name": "japanese_qa_demo_with_haystack_and_es", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2022-12-18 19:21:06", "latest_commit": "2022-12-19 03:57:34", "languages": [ @@ -18616,7 +19008,7 @@ "project_name": "trimatch", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2021-08-30 17:26:15", "latest_commit": "2024-02-08 10:06:06", "languages": [ @@ -18630,7 +19022,7 @@ "project_name": "tantivy-vibrato", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2022-08-25 13:31:30", "latest_commit": "2023-01-19 10:12:17", "languages": [ @@ -18644,7 +19036,7 @@ "project_name": "find-simdoc", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2022-08-31 12:56:10", "latest_commit": "2022-09-27 11:39:27", "languages": [ @@ -18659,7 +19051,7 @@ "project_name": "stringmatch-bench", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2022-09-29 12:24:29", "latest_commit": "2022-09-30 11:36:55", "languages": [ @@ -18674,7 +19066,7 @@ "project_name": "japanki", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2023-10-04 17:43:27", "latest_commit": "2023-10-17 01:00:00", "languages": [ @@ -18688,7 +19080,7 @@ "project_name": "pitch-accent", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2023-08-09 13:36:52", "latest_commit": "2023-09-08 08:19:43", "languages": [ @@ -18704,7 +19096,7 @@ "project_name": "gpt-ja", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2021-06-13 13:14:18", "latest_commit": "2021-09-27 21:08:39", "languages": [ @@ -18718,7 +19110,7 @@ "project_name": "AcademicBART", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2023-01-11 16:19:21", "latest_commit": "2024-07-11 22:09:11", "languages": [ @@ -18732,7 +19124,7 @@ "project_name": "denonbu-ime-dic", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2019-12-30 01:37:16", "latest_commit": "2022-11-13 23:09:25", "languages": [], @@ -18744,7 +19136,7 @@ "project_name": "anthy", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2013-06-30 11:09:24", "latest_commit": "2013-07-27 22:45:26", "languages": [ @@ -18758,7 +19150,7 @@ "project_name": "Data-on-Japanese-Diet-Members", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2022-07-02 22:58:11", "latest_commit": "2022-09-29 13:37:11", "languages": [], @@ -18770,7 +19162,7 @@ "project_name": "ndlngramviewer_v2", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2022-12-26 13:29:58", "latest_commit": "2023-07-20 11:05:53", "languages": [ @@ -18788,7 +19180,7 @@ "project_name": "huggingface-datasets_livedoor-news-corpus", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2023-01-17 23:16:18", "latest_commit": "2023-10-28 14:40:17", "languages": [ @@ -18802,7 +19194,7 @@ "project_name": "jpn_explainable_qa_dataset", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": null, "latest_commit": null, "languages": [], @@ -18814,7 +19206,7 @@ "project_name": "jemhopqa", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2023-08-01 02:07:45", "latest_commit": "2024-06-05 14:54:08", "languages": [ @@ -18828,7 +19220,7 @@ "project_name": "bert-classification-tutorial-2024", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": "2024-05-28 10:50:41", "latest_commit": "2024-07-08 17:10:46", "languages": [ @@ -18842,7 +19234,7 @@ "project_name": "Gemma2_2b_Japanese_finetuning_colab.ipynb", "stargazers_count": 2, "source": "GitHub", - "score": -0.331475011881972, + "score": -0.33023685499248917, "first_commit": null, "latest_commit": null, "languages": [], @@ -18854,7 +19246,7 @@ "project_name": "joint-information-extraction-hs", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2021-11-05 12:32:31", "latest_commit": "2021-11-17 12:29:39", "languages": [ @@ -18869,7 +19261,7 @@ "project_name": "t5_japanese_dialogue_generation", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2021-11-19 18:32:46", "latest_commit": "2021-11-28 10:48:04", "languages": [ @@ -18884,7 +19276,7 @@ "project_name": "lm-evaluation-harness-jp-stable", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2020-08-27 18:08:04", "latest_commit": "2023-06-19 10:48:40", "languages": [ @@ -18899,7 +19291,7 @@ "project_name": "japanese2phoneme", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2021-02-09 16:27:24", "latest_commit": "2022-02-24 16:11:04", "languages": [ @@ -18913,7 +19305,7 @@ "project_name": "anlp_nlp2021_d3-1", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2021-03-12 02:34:47", "latest_commit": "2022-03-08 13:40:28", "languages": [ @@ -18927,7 +19319,7 @@ "project_name": "JDT-with-KenLM-scoring", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2022-06-28 09:22:47", "latest_commit": "2022-07-01 21:29:00", "languages": [ @@ -18941,7 +19333,7 @@ "project_name": "japanese-word-aggregation", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2018-08-08 13:39:47", "latest_commit": "2018-08-20 07:51:01", "languages": [ @@ -18955,7 +19347,7 @@ "project_name": "SAT-for-Japanese", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2022-10-04 23:48:47", "latest_commit": "2022-10-05 00:40:09", "languages": [ @@ -18969,7 +19361,7 @@ "project_name": "japanese_llm_eval", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2024-03-28 14:56:01", "latest_commit": "2024-04-22 07:39:03", "languages": [ @@ -18984,7 +19376,7 @@ "project_name": "qlora_ja", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2023-09-10 15:04:15", "latest_commit": "2024-07-13 10:01:12", "languages": [ @@ -18998,7 +19390,7 @@ "project_name": "japanese-address-parser", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2023-11-17 23:16:38", "latest_commit": "2024-08-12 18:23:09", "languages": [ @@ -19013,7 +19405,7 @@ "project_name": "friendly_JA-Model", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2022-01-10 12:03:59", "latest_commit": "2022-05-22 14:42:46", "languages": [], @@ -19025,7 +19417,7 @@ "project_name": "ChuanhuChatGPTJapanese", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2023-03-02 21:37:13", "latest_commit": "2023-03-07 14:10:10", "languages": [ @@ -19039,7 +19431,7 @@ "project_name": "chrome-ext-translate-to-hiragana-with-chatgpt", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2023-03-25 20:09:31", "latest_commit": "2023-04-01 16:05:53", "languages": [ @@ -19053,7 +19445,7 @@ "project_name": "chatvrm", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2023-04-28 17:25:29", "latest_commit": "2024-07-18 13:49:25", "languages": [ @@ -19068,7 +19460,7 @@ "project_name": "sftly-replace", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2023-05-04 20:51:22", "latest_commit": "2023-05-24 02:03:16", "languages": [ @@ -19082,7 +19474,7 @@ "project_name": "JumanDIC", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2015-12-07 17:42:10", "latest_commit": "2022-08-18 19:01:36", "languages": [ @@ -19098,7 +19490,7 @@ "project_name": "uchinaaguchi_dict", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2024-03-12 06:53:05", "latest_commit": "2024-08-12 17:05:46", "languages": [ @@ -19113,7 +19505,7 @@ "project_name": "skk-jisyo.emoji-ja", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2018-03-13 01:04:56", "latest_commit": "2018-03-13 02:01:32", "languages": [ @@ -19127,7 +19519,7 @@ "project_name": "kokkosho_data", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2017-04-16 15:04:26", "latest_commit": "2019-07-09 23:36:27", "languages": [], @@ -19139,7 +19531,7 @@ "project_name": "isbn4groups", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2022-08-03 16:31:28", "latest_commit": "2024-06-25 14:11:40", "languages": [], @@ -19151,7 +19543,7 @@ "project_name": "jacred", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2024-01-11 16:26:25", "latest_commit": "2024-03-08 17:58:20", "languages": [], @@ -19163,7 +19555,7 @@ "project_name": "jades", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2022-10-15 09:32:35", "latest_commit": "2022-12-13 15:57:29", "languages": [], @@ -19175,7 +19567,7 @@ "project_name": "japanese-ir-tutorial", "stargazers_count": 1, "source": "GitHub", - "score": -0.33440655389456975, + "score": -0.33317687555375886, "first_commit": "2024-04-29 10:52:11", "latest_commit": "2024-06-05 18:56:44", "languages": [ @@ -19189,7 +19581,7 @@ "project_name": "pynormalizenumexp", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2021-10-11 21:02:26", "latest_commit": "2024-04-28 19:55:49", "languages": [ @@ -19197,13 +19589,27 @@ ], "model_or_dataset": null }, + { + "description": "Examples to finetune encoder-only and encoder-decoder transformers for Japanese language (Hugging Face) Resources", + "url": "https://github.com/tsmatz/huggingface-finetune-japanese", + "project_name": "huggingface-finetune-japanese", + "stargazers_count": 0, + "source": "GitHub", + "score": -0.33611689611502854, + "first_commit": "2022-10-24 18:13:22", + "latest_commit": "2023-10-06 17:11:54", + "languages": [ + "Jupyter Notebook" + ], + "model_or_dataset": null + }, { "description": "OCR system for recognizing modern Japanese magazines", "url": "https://github.com/ducanh841988/Kindai-OCR", "project_name": "Kindai-OCR", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2020-07-08 10:12:27", "latest_commit": "2023-07-12 12:14:52", "languages": [ @@ -19217,7 +19623,7 @@ "project_name": "JGLUE-benchmark", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2023-03-18 01:19:37", "latest_commit": "2024-08-09 18:31:33", "languages": [ @@ -19231,7 +19637,7 @@ "project_name": "yubin", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2019-10-28 07:11:54", "latest_commit": "2019-10-28 07:20:26", "languages": [ @@ -19245,7 +19651,7 @@ "project_name": "ASRDeepSpeech", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2020-03-03 15:08:25", "latest_commit": "2022-09-26 00:11:29", "languages": [ @@ -19260,7 +19666,7 @@ "project_name": "radicalchar", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2022-11-29 19:17:38", "latest_commit": "2022-12-30 01:40:44", "languages": [ @@ -19276,7 +19682,7 @@ "project_name": "natsume", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": null, "latest_commit": null, "languages": [], @@ -19288,7 +19694,7 @@ "project_name": "RAG-Japanese", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2023-11-14 14:06:31", "latest_commit": "2023-11-29 19:47:20", "languages": [ @@ -19302,7 +19708,7 @@ "project_name": "jglue-evaluation-scripts", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2023-03-18 01:19:37", "latest_commit": "2024-08-09 18:31:33", "languages": [ @@ -19310,13 +19716,55 @@ ], "model_or_dataset": null }, + { + "description": "Whisperのデコーダをllm-jp-1.3b-v1.0に置き換えた音声認識モデルを学習させるためのコード", + "url": "https://github.com/tosiyuki/llm-jp-asr", + "project_name": "llm-jp-asr", + "stargazers_count": 0, + "source": "GitHub", + "score": -0.33611689611502854, + "first_commit": "2024-09-07 22:07:43", + "latest_commit": "2024-09-07 22:57:13", + "languages": [ + "Python" + ], + "model_or_dataset": null + }, + { + "description": "Open source RAG with Llama Index for Japanese LLM in low resource settting", + "url": "https://github.com/akimfromparis/rag-japanese", + "project_name": "rag-japanese", + "stargazers_count": 0, + "source": "GitHub", + "score": -0.33611689611502854, + "first_commit": "2023-11-14 14:06:31", + "latest_commit": "2023-11-29 19:47:20", + "languages": [ + "Jupyter Notebook" + ], + "model_or_dataset": null + }, + { + "description": "A Japanese Parser (including historical Japanese)", + "url": "https://github.com/komiya-lab/monaka", + "project_name": "monaka", + "stargazers_count": 0, + "source": "GitHub", + "score": -0.33611689611502854, + "first_commit": "2024-01-24 10:26:06", + "latest_commit": "2024-07-16 14:16:00", + "languages": [ + "Python" + ], + "model_or_dataset": null + }, { "description": "日本語文字変換ライブラリ (javascript)", "url": "https://github.com/kazuhikoarase/jaconv", "project_name": "jaconv", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2016-10-22 05:22:02", "latest_commit": "2024-01-20 05:35:13", "languages": [ @@ -19332,7 +19780,7 @@ "project_name": "romaji-conv", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2020-07-05 01:29:36", "latest_commit": "2024-09-01 19:50:38", "languages": [ @@ -19346,7 +19794,7 @@ "project_name": "oskim", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2023-02-24 15:08:36", "latest_commit": "2023-02-24 15:43:20", "languages": [ @@ -19361,7 +19809,7 @@ "project_name": "aovec", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2021-06-22 16:51:15", "latest_commit": "2023-02-01 02:27:34", "languages": [ @@ -19375,7 +19823,7 @@ "project_name": "BERT-Japan-vaccination", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2022-04-05 16:46:38", "latest_commit": "2022-05-23 00:47:45", "languages": [ @@ -19389,7 +19837,7 @@ "project_name": "VRChatGPT", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2023-03-21 19:53:54", "latest_commit": "2023-03-22 21:04:37", "languages": [ @@ -19403,7 +19851,7 @@ "project_name": "chatgpt-prompt-sample-japanese", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2023-04-13 14:22:50", "latest_commit": "2024-08-09 15:15:17", "languages": [], @@ -19415,7 +19863,7 @@ "project_name": "pokemon-ime-dic", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2020-01-10 23:13:19", "latest_commit": "2020-01-10 23:25:48", "languages": [], @@ -19427,7 +19875,7 @@ "project_name": "jitenbot", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": null, "latest_commit": null, "languages": [], @@ -19439,7 +19887,7 @@ "project_name": "azookey-desktop", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2021-09-07 21:50:12", "latest_commit": "2024-08-13 22:08:17", "languages": [ @@ -19453,7 +19901,7 @@ "project_name": "azookeykanakanjiconverter", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2023-05-28 11:51:25", "latest_commit": "2024-08-11 00:53:16", "languages": [ @@ -19467,7 +19915,7 @@ "project_name": "libkkc", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2012-08-07 17:45:52", "latest_commit": "2024-09-02 12:08:48", "languages": [ @@ -19481,7 +19929,7 @@ "project_name": "libskk", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2011-10-05 18:18:07", "latest_commit": "2024-09-02 12:09:00", "languages": [ @@ -19495,7 +19943,7 @@ "project_name": "UD_Japanese-PUD", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2017-05-23 10:31:45", "latest_commit": "2020-05-16 10:57:47", "languages": [], @@ -19507,7 +19955,7 @@ "project_name": "graded-enja-corpus", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2021-06-05 11:55:23", "latest_commit": "2023-03-14 00:24:51", "languages": [ @@ -19521,7 +19969,7 @@ "project_name": "WikipediaWordFrequencyList", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2022-04-17 16:35:32", "latest_commit": "2022-04-17 16:44:19", "languages": [ @@ -19535,7 +19983,7 @@ "project_name": "friendly_JA-Corpus", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": null, "latest_commit": null, "languages": [], @@ -19547,7 +19995,7 @@ "project_name": "copa-japanese", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2023-01-13 09:04:08", "latest_commit": "2023-02-24 11:28:31", "languages": [], @@ -19559,7 +20007,7 @@ "project_name": "huggingface-datasets_CAMERA", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2023-03-17 23:02:32", "latest_commit": "2023-03-17 23:49:35", "languages": [ @@ -19573,7 +20021,7 @@ "project_name": "FactCheckSentenceNLI-FCSNLI-", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2021-02-26 14:08:54", "latest_commit": "2021-03-03 11:15:47", "languages": [ @@ -19587,7 +20035,7 @@ "project_name": "EaST-MELD", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2023-04-12 00:16:46", "latest_commit": "2023-06-23 11:09:20", "languages": [], @@ -19599,7 +20047,7 @@ "project_name": "reazonspeech", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2022-10-19 10:08:01", "latest_commit": "2024-08-01 17:38:15", "languages": [ @@ -19614,7 +20062,7 @@ "project_name": "j-unimorph", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2024-01-10 20:05:15", "latest_commit": "2024-05-12 20:42:38", "languages": [ @@ -19628,7 +20076,7 @@ "project_name": "jmed-llm", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2024-07-11 20:01:36", "latest_commit": "2024-08-10 08:49:25", "languages": [ @@ -19642,7 +20090,7 @@ "project_name": "lawtext", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2017-12-06 23:09:02", "latest_commit": "2024-08-10 23:37:12", "languages": [ @@ -19657,7 +20105,7 @@ "project_name": "nlp2024-tutorial-3", "stargazers_count": 0, "source": "GitHub", - "score": -0.33733809590716757, + "score": -0.33611689611502854, "first_commit": "2024-03-05 09:03:21", "latest_commit": "2024-04-02 14:38:06", "languages": [],