add model.

README.md

@@ -1,3 +1,13 @@
 ---
-license: cc-by-sa-4.0
+license: cc-by-sa-3.0
 ---
+# BERTによる日本語固有表現抽出のモデル
+
+## 事前学習モデル
+[cl-tohoku/bert-base-japanese-v2](https://huggingface.co/cl-tohoku/bert-base-japanese-v2)
+
+## 学習データ
+Wikipediaを用いた日本語の固有表現抽出データセット（[stockmarkteam/ner-wikipedia-dataset](https://github.com/stockmarkteam/ner-wikipedia-dataset)）
+
+## ライセンス
+[Creative Commons Attribution-ShareAlike 3.0](https://creativecommons.org/licenses/by-sa/3.0/)

config.json

@@ -0,0 +1,64 @@
+{
+  "_name_or_path": "cl-tohoku/bert-base-japanese-v2",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-\u4eba\u540d",
+    "2": "I-\u4eba\u540d",
+    "3": "B-\u6cd5\u4eba\u540d",
+    "4": "I-\u6cd5\u4eba\u540d",
+    "5": "B-\u653f\u6cbb\u7684\u7d44\u7e54\u540d",
+    "6": "I-\u653f\u6cbb\u7684\u7d44\u7e54\u540d",
+    "7": "B-\u305d\u306e\u4ed6\u306e\u7d44\u7e54\u540d",
+    "8": "I-\u305d\u306e\u4ed6\u306e\u7d44\u7e54\u540d",
+    "9": "B-\u5730\u540d",
+    "10": "I-\u5730\u540d",
+    "11": "B-\u65bd\u8a2d\u540d",
+    "12": "I-\u65bd\u8a2d\u540d",
+    "13": "B-\u88fd\u54c1\u540d",
+    "14": "I-\u88fd\u54c1\u540d",
+    "15": "B-\u30a4\u30d9\u30f3\u30c8\u540d",
+    "16": "I-\u30a4\u30d9\u30f3\u30c8\u540d"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-\u305d\u306e\u4ed6\u306e\u7d44\u7e54\u540d": 7,
+    "B-\u30a4\u30d9\u30f3\u30c8\u540d": 15,
+    "B-\u4eba\u540d": 1,
+    "B-\u5730\u540d": 9,
+    "B-\u653f\u6cbb\u7684\u7d44\u7e54\u540d": 5,
+    "B-\u65bd\u8a2d\u540d": 11,
+    "B-\u6cd5\u4eba\u540d": 3,
+    "B-\u88fd\u54c1\u540d": 13,
+    "I-\u305d\u306e\u4ed6\u306e\u7d44\u7e54\u540d": 8,
+    "I-\u30a4\u30d9\u30f3\u30c8\u540d": 16,
+    "I-\u4eba\u540d": 2,
+    "I-\u5730\u540d": 10,
+    "I-\u653f\u6cbb\u7684\u7d44\u7e54\u540d": 6,
+    "I-\u65bd\u8a2d\u540d": 12,
+    "I-\u6cd5\u4eba\u540d": 4,
+    "I-\u88fd\u54c1\u540d": 14,
+    "O": 0
+  },
+  "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",
+  "tokenizer_class": "BertJapaneseTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32768
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3b7146238ac2e2a45a7f90ae665b1513c7a764cbd2ef18332bbe9a215f9c907
+size 442589041

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf4850542790f11293c1b30528c68ba8d08368bb635b56198ea87a9d4f75b6e3
+size 442792012

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "do_subword_tokenize": true,
+  "do_word_tokenize": true,
+  "mask_token": "[MASK]",
+  "mecab_kwargs": {
+    "mecab_dic": "unidic_lite"
+  },
+  "name_or_path": "cl-tohoku/bert-base-japanese-v2",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "subword_tokenizer_type": "wordpiece",
+  "tokenizer_class": "BertJapaneseTokenizer",
+  "unk_token": "[UNK]",
+  "word_tokenizer_type": "mecab"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af5169cc5cd8695dfbb4590261fadb2c4876a3e82a537eb9c20215ab28ca587c
+size 3375