rudaoshi commited on
Commit
874b611
·
verified ·
1 Parent(s): 8b36d84

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. config.json +2 -3
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +1 -56
  4. vocab.txt +0 -0
config.json CHANGED
@@ -3,7 +3,6 @@
3
  "BertForMaskedLM"
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
6
- "classifier_dropout": null,
7
  "gradient_checkpointing": false,
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.1,
@@ -17,8 +16,8 @@
17
  "num_hidden_layers": 12,
18
  "pad_token_id": 0,
19
  "position_embedding_type": "absolute",
20
- "transformers_version": "4.57.0",
21
  "type_vocab_size": 2,
22
  "use_cache": true,
23
- "vocab_size": 30522
24
  }
 
3
  "BertForMaskedLM"
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
 
6
  "gradient_checkpointing": false,
7
  "hidden_act": "gelu",
8
  "hidden_dropout_prob": 0.1,
 
16
  "num_hidden_layers": 12,
17
  "pad_token_id": 0,
18
  "position_embedding_type": "absolute",
19
+ "transformers_version": "4.6.0.dev0",
20
  "type_vocab_size": 2,
21
  "use_cache": true,
22
+ "vocab_size": 28996
23
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,56 +1 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "[PAD]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "100": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "101": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "102": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "103": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
- "clean_up_tokenization_spaces": false,
45
- "cls_token": "[CLS]",
46
- "do_lower_case": true,
47
- "extra_special_tokens": {},
48
- "mask_token": "[MASK]",
49
- "model_max_length": 512,
50
- "pad_token": "[PAD]",
51
- "sep_token": "[SEP]",
52
- "strip_accents": null,
53
- "tokenize_chinese_chars": true,
54
- "tokenizer_class": "BertTokenizer",
55
- "unk_token": "[UNK]"
56
- }
 
1
+ {"do_lower_case": false, "model_max_length": 512}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff