wu981526092 commited on
Commit
c0997a2
·
verified ·
1 Parent(s): 57efcbb

Upload 6 files

Browse files
Files changed (5) hide show
  1. config.json +3 -2
  2. model.safetensors +2 -2
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +5 -7
  5. vocab.txt +0 -0
config.json CHANGED
@@ -1,10 +1,11 @@
1
  {
2
- "_name_or_path": "allenai/scibert_scivocab_uncased",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
 
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.1,
10
  "hidden_size": 768,
@@ -58,5 +59,5 @@
58
  "transformers_version": "4.44.2",
59
  "type_vocab_size": 2,
60
  "use_cache": true,
61
- "vocab_size": 31090
62
  }
 
1
  {
2
+ "_name_or_path": "bert-base-uncased",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
 
59
  "transformers_version": "4.44.2",
60
  "type_vocab_size": 2,
61
  "use_cache": true,
62
+ "vocab_size": 30522
63
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:305eb5ca4d4d7a7690a5ce01bf211795b6fbd68a9fc97fd3981341d95ade3136
3
- size 439746608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11f177da17c23d451a0b232d135d691384c9ffbce622bdb3094071386be83554
3
+ size 438001712
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": true
10
  },
11
- "101": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": true
18
  },
19
- "102": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "103": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
@@ -32,7 +32,7 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "104": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
@@ -43,11 +43,9 @@
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
- "do_basic_tokenize": true,
47
  "do_lower_case": true,
48
  "mask_token": "[MASK]",
49
- "model_max_length": 1000000000000000019884624838656,
50
- "never_split": null,
51
  "pad_token": "[PAD]",
52
  "sep_token": "[SEP]",
53
  "strip_accents": null,
 
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "100": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "101": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "102": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "103": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
 
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
 
46
  "do_lower_case": true,
47
  "mask_token": "[MASK]",
48
+ "model_max_length": 512,
 
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff