initial commit

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-m",
+    "2": "B-mo",
+    "3": "B-do",
+    "4": "I-do",
+    "5": "B-r",
+    "6": "I-f",
+    "7": "I-mo",
+    "8": "B-du",
+    "9": "I-r",
+    "10": "I-du",
+    "11": "I-m",
+    "12": "B-f"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-do": 3,
+    "B-du": 8,
+    "B-f": 12,
+    "B-m": 1,
+    "B-mo": 2,
+    "B-r": 5,
+    "I-do": 4,
+    "I-du": 10,
+    "I-f": 6,
+    "I-m": 11,
+    "I-mo": 7,
+    "I-r": 9,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e62d61f244f90a1d0b14d5104233f3ad7760f1467e0eced5616c716a59b70ef8
+size 1336592759

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "bert-large-uncased"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66052220654d7f9a843dee347a13278fe5c5dec19729278799928b3a405ae3ee
+size 2095