Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,133 @@
+---
+language:
+- ja
+base_model: cl-nagoya/ruri-pt-base
+tags:
+- sentence-similarity
+- feature-extraction
+license: apache-2.0
+datasets:
+- cl-nagoya/ruri-dataset-ft
+pipeline_tag: sentence-similarity
+---
+
+# Ruri: Japanese General Text Embeddings
+
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers fugashi sentencepiece unidic-lite
+```
+
+Then you can load this model and run inference.
+```python
+import torch.nn.functional as F
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("cl-nagoya/ruri-base")
+
+# Don't forget to add the prefix "クエリ: " for query-side or "文章: " for passage-side texts.
+sentences = [
+    "クエリ: 瑠璃色はどんな色？",
+    "文章: 瑠璃色（るりいろ）は、紫みを帯びた濃い青。名は、半貴石の瑠璃（ラピスラズリ、英: lapis lazuli）による。JIS慣用色名では「こい紫みの青」（略号 dp-pB）と定義している[1][2]。",
+    "クエリ: ワシやタカのように、鋭いくちばしと爪を持った大型の鳥類を総称して「何類」というでしょう?",
+    "文章: ワシ、タカ、ハゲワシ、ハヤブサ、コンドル、フクロウが代表的である。これらの猛禽類はリンネ前後の時代(17~18世紀)には鷲類・鷹類・隼類及び梟類に分類された。ちなみにリンネは狩りをする鳥を単一の目(もく)にまとめ、vultur(コンドル、ハゲワシ)、falco(ワシ、タカ、ハヤブサなど)、strix(フクロウ)、lanius(モズ)の4属を含めている。",
+]
+
+embeddings = model.encode(sentences, convert_to_tensor=True)
+print(embeddings.size())
+# [4, 768]
+
+similarities = F.cosine_similarity(embeddings.unsqueeze(0), embeddings.unsqueeze(1), dim=2)
+print(similarities)
+# [[1.0000, 0.9421, 0.6844, 0.7167],
+#  [0.9421, 1.0000, 0.6626, 0.6863],
+#  [0.6844, 0.6626, 1.0000, 0.8785],
+#  [0.7167, 0.6863, 0.8785, 1.0000]]
+```
+
+## Benchmarks
+
+### JMTEB
+Evaluated with [JMTEB](https://github.com/sbintuitions/JMTEB).
+
+|Model|#Param.|Avg.|Retrieval|STS|Classfification|Reranking|Clustering|PairClassification|
+|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|
+|[cl-nagoya/sup-simcse-ja-base](https://huggingface.co/cl-nagoya/sup-simcse-ja-base)|111M|68.56|49.64|82.05|73.47|91.83|51.79|62.57|
+|[cl-nagoya/sup-simcse-ja-large](https://huggingface.co/cl-nagoya/sup-simcse-ja-large)|337M|66.51|37.62|83.18|73.73|91.48|50.56|62.51|
+|[cl-nagoya/unsup-simcse-ja-base](https://huggingface.co/cl-nagoya/unsup-simcse-ja-base)|111M|65.07|40.23|78.72|73.07|91.16|44.77|62.44|
+|[cl-nagoya/unsup-simcse-ja-large](https://huggingface.co/cl-nagoya/unsup-simcse-ja-large)|337M|66.27|40.53|80.56|74.66|90.95|48.41|62.49|
+|[pkshatech/GLuCoSE-base-ja](https://huggingface.co/pkshatech/GLuCoSE-base-ja)|133M|70.44|59.02|78.71|76.82|91.90|49.78|66.39|
+||||||||||
+|[sentence-transformers/LaBSE](https://huggingface.co/sentence-transformers/LaBSE)|472M|64.70|40.12|76.56|72.66|91.63|44.88|62.33|
+|[intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small)|118M|69.52|67.27|80.07|67.62|93.03|46.91|62.19|
+|[intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base)|278M|70.12|68.21|79.84|69.30|92.85|48.26|62.26|
+|[intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large)|560M|71.65|70.98|79.70|72.89|92.96|51.24|62.15|
+||||||||||
+|OpenAI/text-embedding-ada-002|-|69.48|64.38|79.02|69.75|93.04|48.30|62.40|
+|OpenAI/text-embedding-3-small|-|70.86|66.39|79.46|73.06|92.92|51.06|62.27|
+|OpenAI/text-embedding-3-large|-|73.97|74.48|82.52|77.58|93.58|53.32|62.35|
+||||||||||
+|[Ruri-Small](https://huggingface.co/cl-nagoya/ruri-small)|68M|71.53|69.41|82.79|76.22|93.00|51.19|62.11|
+|[**Ruri-Base**](https://huggingface.co/cl-nagoya/ruri-base) (this model)|111M|71.91|69.82|82.87|75.58|92.91|54.16|62.38|
+|[Ruri-Large](https://huggingface.co/cl-nagoya/ruri-large)|337M|73.31|73.02|83.13|77.43|92.99|51.82|62.29|
+
+
+
+
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [cl-nagoya/ruri-pt-base](https://huggingface.co/cl-nagoya/ruri-pt-base) 
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768
+- **Similarity Function:** Cosine Similarity
+- **Language:** Japanese
+- **License:** Apache 2.0
+- **Paper:** https://arxiv.org/abs/2409.07737
+<!-- - **Training Dataset:** Unknown -->
+
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+### Framework Versions
+- Python: 3.10.13
+- Sentence Transformers: 3.0.0
+- Transformers: 4.41.2
+- PyTorch: 2.3.1+cu118
+- Accelerate: 0.30.1
+- Datasets: 2.19.1
+- Tokenizers: 0.19.1
+
+## Citation
+
+```bibtex
+@misc{
+  Ruri,
+  title={{Ruri: Japanese General Text Embeddings}}, 
+  author={Hayato Tsukagoshi and Ryohei Sasano},
+  year={2024},
+  eprint={2409.07737},
+  archivePrefix={arXiv},
+  primaryClass={cs.CL},
+  url={https://arxiv.org/abs/2409.07737}, 
+}
+```
+
+## License
+This model is published under the [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0).

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "cl-nagoya/ruri-base-pt",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32768
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.0",
+    "transformers": "4.41.2",
+    "pytorch": "2.3.1+cu118"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

jmteb_config/jmteb.jsonnet

@@ -0,0 +1,22 @@
+// Classification
+(import './tasks/amazon_review_classification.jsonnet') +
+(import './tasks/amazon_counterfactual_classification.jsonnet') +
+(import './tasks/massive_intent_classification.jsonnet') +
+(import './tasks/massive_scenario_classification.jsonnet') +
+// Clustering
+(import './tasks/livedoor_news.jsonnet') +
+(import './tasks/mewsc16.jsonnet') +
+// STS
+(import './tasks/jsts.jsonnet') +
+(import './tasks/jsick.jsonnet') +
+// Pair Classification
+(import './tasks/paws_x_ja.jsonnet') +
+// Retrieval
+(import './tasks/jagovfaqs_22k.jsonnet') +
+(import './tasks/mrtydi.jsonnet') +
+(import './tasks/jaqket.jsonnet') +
+(import './tasks/nlp_journal_title_abs.jsonnet') +
+(import './tasks/nlp_journal_title_intro.jsonnet') +
+(import './tasks/nlp_journal_abs_intro.jsonnet') +
+// Reranking
+(import './tasks/esci.jsonnet')

jmteb_config/tasks/amazon_counterfactual_classification.jsonnet

@@ -0,0 +1,32 @@
+{
+  amazon_counterfactual_classification: {
+    class_path: 'ClassificationEvaluator',
+    init_args: {
+      prefix: 'クエリ: ',
+      train_dataset: {
+        class_path: 'HfClassificationDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'train',
+          name: 'amazon_counterfactual_classification',
+        },
+      },
+      val_dataset: {
+        class_path: 'HfClassificationDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'validation',
+          name: 'amazon_counterfactual_classification',
+        },
+      },
+      test_dataset: {
+        class_path: 'HfClassificationDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'test',
+          name: 'amazon_counterfactual_classification',
+        },
+      },
+    },
+  },
+}

jmteb_config/tasks/amazon_review_classification.jsonnet

@@ -0,0 +1,32 @@
+{
+  amazon_review_classification: {
+    class_path: 'ClassificationEvaluator',
+    init_args: {
+      prefix: 'クエリ: ',
+      train_dataset: {
+        class_path: 'HfClassificationDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'train',
+          name: 'amazon_review_classification',
+        },
+      },
+      val_dataset: {
+        class_path: 'HfClassificationDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'validation',
+          name: 'amazon_review_classification',
+        },
+      },
+      test_dataset: {
+        class_path: 'HfClassificationDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'test',
+          name: 'amazon_review_classification',
+        },
+      },
+    },
+  },
+}

jmteb_config/tasks/esci.jsonnet

@@ -0,0 +1,33 @@
+{
+  esci: {
+    class_path: 'RerankingEvaluator',
+    init_args: {
+      doc_prefix: '文章: ',
+      query_prefix: 'クエリ: ',
+      val_query_dataset: {
+        class_path: 'HfRerankingQueryDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'validation',
+          name: 'esci-query',
+        },
+      },
+      test_query_dataset: {
+        class_path: 'HfRerankingQueryDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'test',
+          name: 'esci-query',
+        },
+      },
+      doc_dataset: {
+        class_path: 'HfRerankingDocDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'corpus',
+          name: 'esci-corpus',
+        },
+      },
+    },
+  },
+}

jmteb_config/tasks/jagovfaqs_22k.jsonnet

@@ -0,0 +1,33 @@
+{
+  jagovfaqs_22k: {
+    class_path: 'RetrievalEvaluator',
+    init_args: {
+      doc_prefix: '文章: ',
+      query_prefix: 'クエリ: ',
+      val_query_dataset: {
+        class_path: 'HfRetrievalQueryDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'validation',
+          name: 'jagovfaqs_22k-query',
+        },
+      },
+      test_query_dataset: {
+        class_path: 'HfRetrievalQueryDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'test',
+          name: 'jagovfaqs_22k-query',
+        },
+      },
+      doc_dataset: {
+        class_path: 'HfRetrievalDocDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'corpus',
+          name: 'jagovfaqs_22k-corpus',
+        },
+      },
+    },
+  },
+}

jmteb_config/tasks/jaqket.jsonnet

@@ -0,0 +1,33 @@
+{
+  jaqket: {
+    class_path: 'RetrievalEvaluator',
+    init_args: {
+      doc_prefix: '文章: ',
+      query_prefix: 'クエリ: ',
+      val_query_dataset: {
+        class_path: 'HfRetrievalQueryDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'validation',
+          name: 'jaqket-query',
+        },
+      },
+      test_query_dataset: {
+        class_path: 'HfRetrievalQueryDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'test',
+          name: 'jaqket-query',
+        },
+      },
+      doc_dataset: {
+        class_path: 'HfRetrievalDocDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'corpus',
+          name: 'jaqket-corpus',
+        },
+      },
+    },
+  },
+}

jmteb_config/tasks/jsick.jsonnet

@@ -0,0 +1,25 @@
+{
+  jsick: {
+    class_path: 'STSEvaluator',
+    init_args: {
+      sentence1_prefix: 'クエリ: ',
+      sentence2_prefix: 'クエリ: ',
+      val_dataset: {
+        class_path: 'HfSTSDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'validation',
+          name: 'jsick',
+        },
+      },
+      test_dataset: {
+        class_path: 'HfSTSDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'test',
+          name: 'jsick',
+        },
+      },
+    },
+  },
+}

jmteb_config/tasks/jsts.jsonnet

@@ -0,0 +1,25 @@
+{
+  jsts: {
+    class_path: 'STSEvaluator',
+    init_args: {
+      sentence1_prefix: 'クエリ: ',
+      sentence2_prefix: 'クエリ: ',
+      val_dataset: {
+        class_path: 'HfSTSDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'train',
+          name: 'jsts',
+        },
+      },
+      test_dataset: {
+        class_path: 'HfSTSDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'test',
+          name: 'jsts',
+        },
+      },
+    },
+  },
+}

jmteb_config/tasks/livedoor_news.jsonnet

@@ -0,0 +1,24 @@
+{
+  livedoor_news: {
+    class_path: 'ClusteringEvaluator',
+    init_args: {
+      prefix: 'クエリ: ',
+      val_dataset: {
+        class_path: 'HfClusteringDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'validation',
+          name: 'livedoor_news',
+        },
+      },
+      test_dataset: {
+        class_path: 'HfClusteringDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'test',
+          name: 'livedoor_news',
+        },
+      },
+    },
+  },
+}

jmteb_config/tasks/massive_intent_classification.jsonnet

@@ -0,0 +1,32 @@
+{
+  massive_intent_classification: {
+    class_path: 'ClassificationEvaluator',
+    init_args: {
+      prefix: 'クエリ: ',
+      train_dataset: {
+        class_path: 'HfClassificationDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'train',
+          name: 'massive_intent_classification',
+        },
+      },
+      val_dataset: {
+        class_path: 'HfClassificationDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'validation',
+          name: 'massive_intent_classification',
+        },
+      },
+      test_dataset: {
+        class_path: 'HfClassificationDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'test',
+          name: 'massive_intent_classification',
+        },
+      },
+    },
+  },
+}

jmteb_config/tasks/massive_scenario_classification.jsonnet

@@ -0,0 +1,32 @@
+{
+  massive_scenario_classification: {
+    class_path: 'ClassificationEvaluator',
+    init_args: {
+      prefix: 'クエリ: ',
+      train_dataset: {
+        class_path: 'HfClassificationDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'train',
+          name: 'massive_scenario_classification',
+        },
+      },
+      val_dataset: {
+        class_path: 'HfClassificationDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'validation',
+          name: 'massive_scenario_classification',
+        },
+      },
+      test_dataset: {
+        class_path: 'HfClassificationDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'test',
+          name: 'massive_scenario_classification',
+        },
+      },
+    },
+  },
+}

jmteb_config/tasks/mewsc16.jsonnet

@@ -0,0 +1,24 @@
+{
+  mewsc16: {
+    class_path: 'ClusteringEvaluator',
+    init_args: {
+      prefix: 'クエリ: ',
+      val_dataset: {
+        class_path: 'HfClusteringDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'validation',
+          name: 'mewsc16_ja',
+        },
+      },
+      test_dataset: {
+        class_path: 'HfClusteringDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'test',
+          name: 'mewsc16_ja',
+        },
+      },
+    },
+  },
+}

jmteb_config/tasks/mrtydi.jsonnet

@@ -0,0 +1,33 @@
+{
+  mrtydi: {
+    class_path: 'RetrievalEvaluator',
+    init_args: {
+      doc_prefix: '文章: ',
+      query_prefix: 'クエリ: ',
+      val_query_dataset: {
+        class_path: 'HfRetrievalQueryDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'validation',
+          name: 'mrtydi-query',
+        },
+      },
+      test_query_dataset: {
+        class_path: 'HfRetrievalQueryDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'test',
+          name: 'mrtydi-query',
+        },
+      },
+      doc_dataset: {
+        class_path: 'HfRetrievalDocDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'corpus',
+          name: 'mrtydi-corpus',
+        },
+      },
+    },
+  },
+}

jmteb_config/tasks/nlp_journal_abs_intro.jsonnet

@@ -0,0 +1,33 @@
+{
+  nlp_journal_abs_intro: {
+    class_path: 'RetrievalEvaluator',
+    init_args: {
+      doc_prefix: '文章: ',
+      query_prefix: '文章: ',
+      val_query_dataset: {
+        class_path: 'HfRetrievalQueryDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'validation',
+          name: 'nlp_journal_abs_intro-query',
+        },
+      },
+      test_query_dataset: {
+        class_path: 'HfRetrievalQueryDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'test',
+          name: 'nlp_journal_abs_intro-query',
+        },
+      },
+      doc_dataset: {
+        class_path: 'HfRetrievalDocDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'corpus',
+          name: 'nlp_journal_abs_intro-corpus',
+        },
+      },
+    },
+  },
+}

jmteb_config/tasks/nlp_journal_title_abs.jsonnet

@@ -0,0 +1,33 @@
+{
+  nlp_journal_title_abs: {
+    class_path: 'RetrievalEvaluator',
+    init_args: {
+      doc_prefix: '文章: ',
+      query_prefix: 'クエリ: ',
+      val_query_dataset: {
+        class_path: 'HfRetrievalQueryDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'validation',
+          name: 'nlp_journal_title_abs-query',
+        },
+      },
+      test_query_dataset: {
+        class_path: 'HfRetrievalQueryDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'test',
+          name: 'nlp_journal_title_abs-query',
+        },
+      },
+      doc_dataset: {
+        class_path: 'HfRetrievalDocDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'corpus',
+          name: 'nlp_journal_title_abs-corpus',
+        },
+      },
+    },
+  },
+}

jmteb_config/tasks/nlp_journal_title_intro.jsonnet

@@ -0,0 +1,33 @@
+{
+  nlp_journal_title_intro: {
+    class_path: 'RetrievalEvaluator',
+    init_args: {
+      doc_prefix: '文章: ',
+      query_prefix: 'クエリ: ',
+      val_query_dataset: {
+        class_path: 'HfRetrievalQueryDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'validation',
+          name: 'nlp_journal_title_intro-query',
+        },
+      },
+      test_query_dataset: {
+        class_path: 'HfRetrievalQueryDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'test',
+          name: 'nlp_journal_title_intro-query',
+        },
+      },
+      doc_dataset: {
+        class_path: 'HfRetrievalDocDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'corpus',
+          name: 'nlp_journal_title_intro-corpus',
+        },
+      },
+    },
+  },
+}

jmteb_config/tasks/paws_x_ja.jsonnet

@@ -0,0 +1,25 @@
+{
+  paws_x_ja: {
+    class_path: 'PairClassificationEvaluator',
+    init_args: {
+      sentence1_prefix: 'クエリ: ',
+      sentence2_prefix: 'クエリ: ',
+      val_dataset: {
+        class_path: 'HfPairClassificationDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'validation',
+          name: 'paws_x_ja',
+        },
+      },
+      test_dataset: {
+        class_path: 'HfPairClassificationDataset',
+        init_args: {
+          path: 'sbintuitions/JMTEB',
+          split: 'test',
+          name: 'paws_x_ja',
+        },
+      },
+    },
+  },
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e863b345faba4d2fb42a8bf0270e52c3391225d6eb08f213046d46caddba6df
+size 222436792

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

result/Classification/scores_amazon_counterfactual_classification.json

@@ -0,0 +1,23 @@
+{
+    "metric_name": "macro_f1",
+    "metric_value": 0.7665550732749669,
+    "details": {
+        "optimal_classifier_name": "logreg",
+        "val_scores": {
+            "knn_cosine_k_2": {
+                "accuracy": 0.9098712446351931,
+                "macro_f1": 0.6139035745285253
+            },
+            "logreg": {
+                "accuracy": 0.9206008583690987,
+                "macro_f1": 0.7381028328396749
+            }
+        },
+        "test_scores": {
+            "logreg": {
+                "accuracy": 0.923982869379015,
+                "macro_f1": 0.7665550732749669
+            }
+        }
+    }
+}

result/Classification/scores_amazon_review_classification.json

@@ -0,0 +1,23 @@
+{
+    "metric_name": "macro_f1",
+    "metric_value": 0.5575876111411316,
+    "details": {
+        "optimal_classifier_name": "logreg",
+        "val_scores": {
+            "knn_cosine_k_2": {
+                "accuracy": 0.4314,
+                "macro_f1": 0.4209604852624187
+            },
+            "logreg": {
+                "accuracy": 0.5702,
+                "macro_f1": 0.5653832808449197
+            }
+        },
+        "test_scores": {
+            "logreg": {
+                "accuracy": 0.562,
+                "macro_f1": 0.5575876111411316
+            }
+        }
+    }
+}

result/Classification/scores_massive_intent_classification.json

@@ -0,0 +1,23 @@
+{
+    "metric_name": "macro_f1",
+    "metric_value": 0.8141210121425055,
+    "details": {
+        "optimal_classifier_name": "logreg",
+        "val_scores": {
+            "knn_cosine_k_2": {
+                "accuracy": 0.7757009345794392,
+                "macro_f1": 0.7456574019302791
+            },
+            "logreg": {
+                "accuracy": 0.8421052631578947,
+                "macro_f1": 0.8271757887821682
+            }
+        },
+        "test_scores": {
+            "logreg": {
+                "accuracy": 0.8416274377942166,
+                "macro_f1": 0.8141210121425055
+            }
+        }
+    }
+}

result/Classification/scores_massive_scenario_classification.json

@@ -0,0 +1,23 @@
+{
+    "metric_name": "macro_f1",
+    "metric_value": 0.8848812917656395,
+    "details": {
+        "optimal_classifier_name": "logreg",
+        "val_scores": {
+            "knn_cosine_k_2": {
+                "accuracy": 0.8657156910969012,
+                "macro_f1": 0.8581068338871749
+            },
+            "logreg": {
+                "accuracy": 0.8898180029513035,
+                "macro_f1": 0.887764836229313
+            }
+        },
+        "test_scores": {
+            "logreg": {
+                "accuracy": 0.8860121049092132,
+                "macro_f1": 0.8848812917656395
+            }
+        }
+    }
+}

result/Clustering/scores_livedoor_news.json

@@ -0,0 +1,36 @@
+{
+    "metric_name": "v_measure_score",
+    "metric_value": 0.5427223607801758,
+    "details": {
+        "optimal_clustering_model_name": "BisectingKMeans",
+        "val_scores": {
+            "MiniBatchKMeans": {
+                "v_measure_score": 0.5453092926343514,
+                "homogeneity_score": 0.5376167786682042,
+                "completeness_score": 0.5532251395371498
+            },
+            "AgglomerativeClustering": {
+                "v_measure_score": 0.5221218542278205,
+                "homogeneity_score": 0.5145096860981694,
+                "completeness_score": 0.5299626488611732
+            },
+            "BisectingKMeans": {
+                "v_measure_score": 0.5498693214751904,
+                "homogeneity_score": 0.5475063196854639,
+                "completeness_score": 0.552252808804315
+            },
+            "Birch": {
+                "v_measure_score": 0.5208037508658081,
+                "homogeneity_score": 0.5132767763409753,
+                "completeness_score": 0.5285547703444661
+            }
+        },
+        "test_scores": {
+            "BisectingKMeans": {
+                "v_measure_score": 0.5427223607801758,
+                "homogeneity_score": 0.5417341205522448,
+                "completeness_score": 0.5437142131253088
+            }
+        }
+    }
+}

result/Clustering/scores_mewsc16.json

@@ -0,0 +1,36 @@
+{
+    "metric_name": "v_measure_score",
+    "metric_value": 0.5404099864321413,
+    "details": {
+        "optimal_clustering_model_name": "AgglomerativeClustering",
+        "val_scores": {
+            "MiniBatchKMeans": {
+                "v_measure_score": 0.502791381026052,
+                "homogeneity_score": 0.5517784337158165,
+                "completeness_score": 0.46179324043437603
+            },
+            "AgglomerativeClustering": {
+                "v_measure_score": 0.5302546097654716,
+                "homogeneity_score": 0.5735135314580632,
+                "completeness_score": 0.4930638394517115
+            },
+            "BisectingKMeans": {
+                "v_measure_score": 0.48656257334532493,
+                "homogeneity_score": 0.5342920872487864,
+                "completeness_score": 0.4466613135580361
+            },
+            "Birch": {
+                "v_measure_score": 0.49305647750510134,
+                "homogeneity_score": 0.5374392451928177,
+                "completeness_score": 0.45544495608862656
+            }
+        },
+        "test_scores": {
+            "AgglomerativeClustering": {
+                "v_measure_score": 0.5404099864321413,
+                "homogeneity_score": 0.5789428395923124,
+                "completeness_score": 0.5066863291321174
+            }
+        }
+    }
+}

result/PairClassification/scores_paws_x_ja.json

@@ -0,0 +1,41 @@
+{
+    "metric_name": "binary_f1",
+    "metric_value": 0.6237623762376238,
+    "details": {
+        "optimal_distance_metric": "euclidean_distances",
+        "val_scores": {
+            "cosine_distances": {
+                "accuracy": 0.5725,
+                "accuracy_threshold": 0.6920696496963501,
+                "binary_f1": 0.5979670522257273,
+                "binary_f1_threshold": 1.0
+            },
+            "manhatten_distances": {
+                "accuracy": 0.6015,
+                "accuracy_threshold": 19.63576316833496,
+                "binary_f1": 0.6017636684303351,
+                "binary_f1_threshold": 274.46441650390625
+            },
+            "euclidean_distances": {
+                "accuracy": 0.602,
+                "accuracy_threshold": 0.9731899499893188,
+                "binary_f1": 0.6019760056457304,
+                "binary_f1_threshold": 12.281266212463379
+            },
+            "dot_similarities": {
+                "accuracy": 0.574,
+                "accuracy_threshold": 332.39276123046875,
+                "binary_f1": 0.6014825273561596,
+                "binary_f1_threshold": 263.39337158203125
+            }
+        },
+        "test_scores": {
+            "euclidean_distances": {
+                "accuracy": 0.566,
+                "accuracy_threshold": 0.9731899499893188,
+                "binary_f1": 0.6237623762376238,
+                "binary_f1_threshold": 12.281266212463379
+            }
+        }
+    }
+}

result/Reranking/scores_esci.json

@@ -0,0 +1,31 @@
+{
+    "metric_name": "ndcg@10",
+    "metric_value": 0.9290942178703699,
+    "details": {
+        "optimal_distance_metric": "cosine_similarity",
+        "val_scores": {
+            "cosine_similarity": {
+                "ndcg@10": 0.9419326097489188,
+                "ndcg@20": 0.9546274758967366,
+                "ndcg@40": 0.9625015652058491
+            },
+            "dot_score": {
+                "ndcg@10": 0.933159692803982,
+                "ndcg@20": 0.9482607249371672,
+                "ndcg@40": 0.956621759096631
+            },
+            "euclidean_distance": {
+                "ndcg@10": 0.9418339438093611,
+                "ndcg@20": 0.9547832679237122,
+                "ndcg@40": 0.9627457241783169
+            }
+        },
+        "test_scores": {
+            "cosine_similarity": {
+                "ndcg@10": 0.9290942178703699,
+                "ndcg@20": 0.9467035648480672,
+                "ndcg@40": 0.9563220304481116
+            }
+        }
+    }
+}

result/Retrieval/scores_jagovfaqs_22k.json

@@ -0,0 +1,43 @@
+{
+    "metric_name": "ndcg@10",
+    "metric_value": 0.7455660589538348,
+    "details": {
+        "optimal_distance_metric": "euclidean_distance",
+        "val_scores": {
+            "cosine_similarity": {
+                "accuracy@1": 0.6042702544603685,
+                "accuracy@3": 0.7853173442527055,
+                "accuracy@5": 0.830944720678561,
+                "accuracy@10": 0.8821292775665399,
+                "ndcg@10": 0.7477862730518441,
+                "mrr@10": 0.7043207426287267
+            },
+            "dot_score": {
+                "accuracy@1": 0.4597835624451594,
+                "accuracy@3": 0.6607195086282539,
+                "accuracy@5": 0.7282831237203861,
+                "accuracy@10": 0.80549868382568,
+                "ndcg@10": 0.630976061323317,
+                "mrr@10": 0.5752777429583498
+            },
+            "euclidean_distance": {
+                "accuracy@1": 0.6092424685580579,
+                "accuracy@3": 0.7861947937993565,
+                "accuracy@5": 0.8283123720386077,
+                "accuracy@10": 0.8780345130155016,
+                "ndcg@10": 0.7480985513112418,
+                "mrr@10": 0.7060561428432148
+            }
+        },
+        "test_scores": {
+            "euclidean_distance": {
+                "accuracy@1": 0.6035087719298246,
+                "accuracy@3": 0.7795321637426901,
+                "accuracy@5": 0.8277777777777777,
+                "accuracy@10": 0.881578947368421,
+                "ndcg@10": 0.7455660589538348,
+                "mrr@10": 0.7017308317089019
+            }
+        }
+    }
+}

result/Retrieval/scores_jaqket.json

@@ -0,0 +1,43 @@
+{
+    "metric_name": "ndcg@10",
+    "metric_value": 0.5012253145754781,
+    "details": {
+        "optimal_distance_metric": "cosine_similarity",
+        "val_scores": {
+            "cosine_similarity": {
+                "accuracy@1": 0.3407035175879397,
+                "accuracy@3": 0.521608040201005,
+                "accuracy@5": 0.6040201005025125,
+                "accuracy@10": 0.6894472361809045,
+                "ndcg@10": 0.5074962109064866,
+                "mrr@10": 0.44994017707585504
+            },
+            "dot_score": {
+                "accuracy@1": 0.31055276381909547,
+                "accuracy@3": 0.507537688442211,
+                "accuracy@5": 0.5738693467336683,
+                "accuracy@10": 0.6804020100502512,
+                "ndcg@10": 0.48656131133927916,
+                "mrr@10": 0.42555116854111785
+            },
+            "euclidean_distance": {
+                "accuracy@1": 0.3055276381909548,
+                "accuracy@3": 0.4814070351758794,
+                "accuracy@5": 0.5597989949748744,
+                "accuracy@10": 0.6391959798994975,
+                "ndcg@10": 0.4655083260444005,
+                "mrr@10": 0.4106070032703195
+            }
+        },
+        "test_scores": {
+            "cosine_similarity": {
+                "accuracy@1": 0.3159478435305918,
+                "accuracy@3": 0.526579739217653,
+                "accuracy@5": 0.60481444332999,
+                "accuracy@10": 0.6920762286860582,
+                "ndcg@10": 0.5012253145754781,
+                "mrr@10": 0.4404156915190016
+            }
+        }
+    }
+}

result/Retrieval/scores_mrtydi.json

@@ -0,0 +1,43 @@
+{
+    "metric_name": "ndcg@10",
+    "metric_value": 0.3545113073009125,
+    "details": {
+        "optimal_distance_metric": "euclidean_distance",
+        "val_scores": {
+            "cosine_similarity": {
+                "accuracy@1": 0.22306034482758622,
+                "accuracy@3": 0.37176724137931033,
+                "accuracy@5": 0.4536637931034483,
+                "accuracy@10": 0.5549568965517241,
+                "ndcg@10": 0.37815020333355365,
+                "mrr@10": 0.3228995621236997
+            },
+            "dot_score": {
+                "accuracy@1": 0.13793103448275862,
+                "accuracy@3": 0.2704741379310345,
+                "accuracy@5": 0.3394396551724138,
+                "accuracy@10": 0.4170258620689655,
+                "ndcg@10": 0.2698064952674162,
+                "mrr@10": 0.22368979200875752
+            },
+            "euclidean_distance": {
+                "accuracy@1": 0.22844827586206898,
+                "accuracy@3": 0.38362068965517243,
+                "accuracy@5": 0.4665948275862069,
+                "accuracy@10": 0.5668103448275862,
+                "ndcg@10": 0.38745306818571434,
+                "mrr@10": 0.33128378147235893
+            }
+        },
+        "test_scores": {
+            "euclidean_distance": {
+                "accuracy@1": 0.23194444444444445,
+                "accuracy@3": 0.3888888888888889,
+                "accuracy@5": 0.46805555555555556,
+                "accuracy@10": 0.5708333333333333,
+                "ndcg@10": 0.3545113073009125,
+                "mrr@10": 0.3320238095238095
+            }
+        }
+    }
+}

result/Retrieval/scores_nlp_journal_abs_intro.json

@@ -0,0 +1,43 @@
+{
+    "metric_name": "ndcg@10",
+    "metric_value": 0.8689204088388403,
+    "details": {
+        "optimal_distance_metric": "cosine_similarity",
+        "val_scores": {
+            "cosine_similarity": {
+                "accuracy@1": 0.85,
+                "accuracy@3": 0.93,
+                "accuracy@5": 0.93,
+                "accuracy@10": 0.95,
+                "ndcg@10": 0.9031188595062929,
+                "mrr@10": 0.8877777777777779
+            },
+            "dot_score": {
+                "accuracy@1": 0.75,
+                "accuracy@3": 0.87,
+                "accuracy@5": 0.88,
+                "accuracy@10": 0.91,
+                "ndcg@10": 0.8329701303885662,
+                "mrr@10": 0.8079563492063491
+            },
+            "euclidean_distance": {
+                "accuracy@1": 0.83,
+                "accuracy@3": 0.92,
+                "accuracy@5": 0.93,
+                "accuracy@10": 0.94,
+                "ndcg@10": 0.8903171995628786,
+                "mrr@10": 0.87375
+            }
+        },
+        "test_scores": {
+            "cosine_similarity": {
+                "accuracy@1": 0.7945544554455446,
+                "accuracy@3": 0.8836633663366337,
+                "accuracy@5": 0.9084158415841584,
+                "accuracy@10": 0.943069306930693,
+                "ndcg@10": 0.8689204088388403,
+                "mrr@10": 0.8452508643721514
+            }
+        }
+    }
+}

result/Retrieval/scores_nlp_journal_title_abs.json

@@ -0,0 +1,43 @@
+{
+    "metric_name": "ndcg@10",
+    "metric_value": 0.9656989703684407,
+    "details": {
+        "optimal_distance_metric": "cosine_similarity",
+        "val_scores": {
+            "cosine_similarity": {
+                "accuracy@1": 0.9,
+                "accuracy@3": 0.96,
+                "accuracy@5": 0.98,
+                "accuracy@10": 0.99,
+                "ndcg@10": 0.9477320812882918,
+                "mrr@10": 0.9339444444444445
+            },
+            "dot_score": {
+                "accuracy@1": 0.82,
+                "accuracy@3": 0.92,
+                "accuracy@5": 0.94,
+                "accuracy@10": 0.96,
+                "ndcg@10": 0.8940025955079818,
+                "mrr@10": 0.8724285714285713
+            },
+            "euclidean_distance": {
+                "accuracy@1": 0.89,
+                "accuracy@3": 0.97,
+                "accuracy@5": 0.98,
+                "accuracy@10": 0.99,
+                "ndcg@10": 0.9453171995628784,
+                "mrr@10": 0.9304166666666666
+            }
+        },
+        "test_scores": {
+            "cosine_similarity": {
+                "accuracy@1": 0.9306930693069307,
+                "accuracy@3": 0.9777227722772277,
+                "accuracy@5": 0.9876237623762376,
+                "accuracy@10": 0.995049504950495,
+                "ndcg@10": 0.9656989703684407,
+                "mrr@10": 0.955987741631306
+            }
+        }
+    }
+}

result/Retrieval/scores_nlp_journal_title_intro.json

@@ -0,0 +1,43 @@
+{
+    "metric_name": "ndcg@10",
+    "metric_value": 0.7531306059721564,
+    "details": {
+        "optimal_distance_metric": "cosine_similarity",
+        "val_scores": {
+            "cosine_similarity": {
+                "accuracy@1": 0.57,
+                "accuracy@3": 0.8,
+                "accuracy@5": 0.83,
+                "accuracy@10": 0.9,
+                "ndcg@10": 0.7448902792577736,
+                "mrr@10": 0.6942023809523811
+            },
+            "dot_score": {
+                "accuracy@1": 0.49,
+                "accuracy@3": 0.68,
+                "accuracy@5": 0.71,
+                "accuracy@10": 0.83,
+                "ndcg@10": 0.6537395005077568,
+                "mrr@10": 0.5984801587301588
+            },
+            "euclidean_distance": {
+                "accuracy@1": 0.58,
+                "accuracy@3": 0.75,
+                "accuracy@5": 0.85,
+                "accuracy@10": 0.9,
+                "ndcg@10": 0.7411266935263704,
+                "mrr@10": 0.6896904761904763
+            }
+        },
+        "test_scores": {
+            "cosine_similarity": {
+                "accuracy@1": 0.6237623762376238,
+                "accuracy@3": 0.7896039603960396,
+                "accuracy@5": 0.8242574257425742,
+                "accuracy@10": 0.8811881188118812,
+                "ndcg@10": 0.7531306059721564,
+                "mrr@10": 0.7120059327361306
+            }
+        }
+    }
+}

result/STS/scores_jsick.json

@@ -0,0 +1,31 @@
+{
+    "metric_name": "spearman",
+    "metric_value": 0.8231772134744029,
+    "details": {
+        "optimal_similarity_metric": "cosine_similarity",
+        "val_scores": {
+            "cosine_similarity": {
+                "pearson": 0.8390312744889947,
+                "spearman": 0.8309726355825223
+            },
+            "manhatten_distance": {
+                "pearson": 0.8439757378089565,
+                "spearman": 0.8296746939532708
+            },
+            "euclidean_distance": {
+                "pearson": 0.8439757378089565,
+                "spearman": 0.8296746939532708
+            },
+            "dot_score": {
+                "pearson": 0.8235943624962084,
+                "spearman": 0.8066842966908715
+            }
+        },
+        "test_scores": {
+            "cosine_similarity": {
+                "pearson": 0.8323321086750828,
+                "spearman": 0.8231772134744029
+            }
+        }
+    }
+}

result/STS/scores_jsts.json

@@ -0,0 +1,31 @@
+{
+    "metric_name": "spearman",
+    "metric_value": 0.8342848039994751,
+    "details": {
+        "optimal_similarity_metric": "manhatten_distance",
+        "val_scores": {
+            "cosine_similarity": {
+                "pearson": 0.8402004412140045,
+                "spearman": 0.7947630577888891
+            },
+            "manhatten_distance": {
+                "pearson": 0.8359705278620446,
+                "spearman": 0.7954996671020325
+            },
+            "euclidean_distance": {
+                "pearson": 0.8359705278620446,
+                "spearman": 0.7954996671020325
+            },
+            "dot_score": {
+                "pearson": 0.8146522053769387,
+                "spearman": 0.7576805023715597
+            }
+        },
+        "test_scores": {
+            "manhatten_distance": {
+                "pearson": 0.8665411120423515,
+                "spearman": 0.8342848039994751
+            }
+        }
+    }
+}

result/summary.json

@@ -0,0 +1,62 @@
+{
+    "Classification": {
+        "amazon_counterfactual_classification": {
+            "macro_f1": 0.7665550732749669
+        },
+        "amazon_review_classification": {
+            "macro_f1": 0.5575876111411316
+        },
+        "massive_intent_classification": {
+            "macro_f1": 0.8141210121425055
+        },
+        "massive_scenario_classification": {
+            "macro_f1": 0.8848812917656395
+        }
+    },
+    "Reranking": {
+        "esci": {
+            "ndcg@10": 0.9290942178703699
+        }
+    },
+    "Retrieval": {
+        "jagovfaqs_22k": {
+            "ndcg@10": 0.7455660589538348
+        },
+        "jaqket": {
+            "ndcg@10": 0.5012253145754781
+        },
+        "mrtydi": {
+            "ndcg@10": 0.3545113073009125
+        },
+        "nlp_journal_abs_intro": {
+            "ndcg@10": 0.8689204088388403
+        },
+        "nlp_journal_title_abs": {
+            "ndcg@10": 0.9656989703684407
+        },
+        "nlp_journal_title_intro": {
+            "ndcg@10": 0.7531306059721564
+        }
+    },
+    "STS": {
+        "jsick": {
+            "spearman": 0.8231772134744029
+        },
+        "jsts": {
+            "spearman": 0.8342848039994751
+        }
+    },
+    "Clustering": {
+        "livedoor_news": {
+            "v_measure_score": 0.5427223607801758
+        },
+        "mewsc16": {
+            "v_measure_score": 0.5404099864321413
+        }
+    },
+    "PairClassification": {
+        "paws_x_ja": {
+            "binary_f1": 0.6237623762376238
+        }
+    }
+}

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c564888dbafbfebcc7a62d2f4049afe83e6fb5acd50a97082a84407c77ddd8ff
+size 17082922

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "do_subword_tokenize": true,
+  "do_word_tokenize": true,
+  "jumanpp_kwargs": null,
+  "mask_token": "[MASK]",
+  "mecab_kwargs": {
+    "mecab_dic": "unidic_lite"
+  },
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "subword_tokenizer_type": "wordpiece",
+  "sudachi_kwargs": null,
+  "tokenizer_class": "BertJapaneseTokenizer",
+  "unk_token": "[UNK]",
+  "word_tokenizer_type": "mecab"
+}