initial release

README.md

@@ -0,0 +1,30 @@
+---
+language:
+- "ja"
+tags:
+- "japanese"
+- "token-classification"
+- "pos"
+license: "cc-by-sa-4.0"
+pipeline_tag: "token-classification"
+widget:
+- text: "国境の長いトンネルを抜けると雪国であった。"
+---
+
+# roberta-large-japanese-luw-upos
+
+## Model Description
+
+This is a RoBERTa model pre-trained on Japanese 青空文庫 texts for POS-tagging, derived from [roberta-large-japanese-aozora](https://huggingface.co/KoichiYasuoka/roberta-large-japanese-aozora). Every long-unit-word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech).
+
+## How to Use
+
+```py
+from transformers import AutoTokenizer,AutoModelForTokenClassification,TokenClassificationPipeline
+tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/roberta-large-japanese-luw-upos")
+model=AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/roberta-large-japanese-luw-upos")
+pipeline=TokenClassificationPipeline(tokenizer=tokenizer,model=model,aggregation_strategy="simple")
+nlp=lambda x:[(x[t["start"]:t["end"]],t["entity_group"]) for t in pipeline(x)]
+print(nlp("国境の長いトンネルを抜けると雪国であった。"))
+```
+

config.json

@@ -0,0 +1,129 @@
+{
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 2,
+  "classifier_dropout": null,
+  "eos_token_id": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "ADP",
+    "1": "B-NOUN",
+    "2": "ADJ",
+    "3": "B-CCONJ",
+    "4": "DET",
+    "5": "I-ADJ",
+    "6": "B-NUM",
+    "7": "X",
+    "8": "SCONJ",
+    "9": "I-NUM",
+    "10": "NUM",
+    "11": "I-DET",
+    "12": "B-PART",
+    "13": "B-INTJ",
+    "14": "I-CCONJ",
+    "15": "I-VERB",
+    "16": "B-SCONJ",
+    "17": "I-PROPN",
+    "18": "B-PRON",
+    "19": "PROPN",
+    "20": "B-DET",
+    "21": "I-PRON",
+    "22": "B-PROPN",
+    "23": "B-ADP",
+    "24": "I-ADV",
+    "25": "I-INTJ",
+    "26": "B-AUX",
+    "27": "B-VERB",
+    "28": "B-X",
+    "29": "PUNCT",
+    "30": "I-NOUN",
+    "31": "I-SCONJ",
+    "32": "I-PART",
+    "33": "I-X",
+    "34": "PRON",
+    "35": "AUX",
+    "36": "NOUN",
+    "37": "VERB",
+    "38": "B-SYM",
+    "39": "ADV",
+    "40": "PART",
+    "41": "SYM",
+    "42": "I-AUX",
+    "43": "B-ADV",
+    "44": "I-ADP",
+    "45": "B-ADJ",
+    "46": "I-SYM",
+    "47": "CCONJ",
+    "48": "INTJ"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "ADJ": 2,
+    "ADP": 0,
+    "ADV": 39,
+    "AUX": 35,
+    "B-ADJ": 45,
+    "B-ADP": 23,
+    "B-ADV": 43,
+    "B-AUX": 26,
+    "B-CCONJ": 3,
+    "B-DET": 20,
+    "B-INTJ": 13,
+    "B-NOUN": 1,
+    "B-NUM": 6,
+    "B-PART": 12,
+    "B-PRON": 18,
+    "B-PROPN": 22,
+    "B-SCONJ": 16,
+    "B-SYM": 38,
+    "B-VERB": 27,
+    "B-X": 28,
+    "CCONJ": 47,
+    "DET": 4,
+    "I-ADJ": 5,
+    "I-ADP": 44,
+    "I-ADV": 24,
+    "I-AUX": 42,
+    "I-CCONJ": 14,
+    "I-DET": 11,
+    "I-INTJ": 25,
+    "I-NOUN": 30,
+    "I-NUM": 9,
+    "I-PART": 32,
+    "I-PRON": 21,
+    "I-PROPN": 17,
+    "I-SCONJ": 31,
+    "I-SYM": 46,
+    "I-VERB": 15,
+    "I-X": 33,
+    "INTJ": 48,
+    "NOUN": 36,
+    "NUM": 10,
+    "PART": 40,
+    "PRON": 34,
+    "PROPN": 19,
+    "PUNCT": 29,
+    "SCONJ": 8,
+    "SYM": 41,
+    "VERB": 37,
+    "X": 7
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "RemBertTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250315
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29c3f528e4556e8443c0dc0ae624d670cf0a0414894e4c1c0a5b0ad0ae21f51d
+size 2237010963

sentencepiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01ba4719c80b6fe911b091a7c05124b64eeece964e09c058ef8f9805daca546b
+size 1

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "tokenizer_class": "RemBertTokenizerFast"}