Fei-Wang commited on
Commit
05a7891
·
1 Parent(s): b7986b3

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +50 -0
  2. special_tokens_map.json +7 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +14 -0
  5. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-chinese",
3
+ "architectures": [
4
+ "MyBertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "hidden_size1": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-\u7701",
16
+ "2": "I-\u7701",
17
+ "3": "B-\u533a\u53bf\u5e02",
18
+ "4": "I-\u533a\u53bf\u5e02",
19
+ "5": "B-\u8be6\u7ec6\u5730\u5740",
20
+ "6": "I-\u8be6\u7ec6\u5730\u5740"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "B-\u533a\u53bf\u5e02": 3,
26
+ "B-\u7701": 1,
27
+ "B-\u8be6\u7ec6\u5730\u5740": 5,
28
+ "I-\u533a\u53bf\u5e02": 4,
29
+ "I-\u7701": 2,
30
+ "I-\u8be6\u7ec6\u5730\u5740": 6,
31
+ "O": 0
32
+ },
33
+ "layer_norm_eps": 1e-12,
34
+ "max_position_embeddings": 512,
35
+ "model_type": "mybert",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 12,
38
+ "pad_token_id": 0,
39
+ "pooler_fc_size": 768,
40
+ "pooler_num_attention_heads": 12,
41
+ "pooler_num_fc_layers": 3,
42
+ "pooler_size_per_head": 128,
43
+ "pooler_type": "first_token_transform",
44
+ "position_embedding_type": "absolute",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.25.1",
47
+ "type_vocab_size": 2,
48
+ "use_cache": true,
49
+ "vocab_size": 21128
50
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": false,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "bert-base-chinese",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff