Hugging Face's logo

vkimbris
/
wb-charcs-extraction

Token Classification
Transformers
Safetensors
bert
Inference Endpoints
Model card Files Community
vkimbris commited on
Commit
37f64ea
•
1 Parent(s): 41734f4

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +5 -35
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +5 -12
  4. vocab.txt +0 -0
special_tokens_map.json CHANGED
@@ -1,37 +1,7 @@
1
  {
2
- "cls_token": {
3
- "content": "[CLS]",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "mask_token": {
10
- "content": "[MASK]",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "[PAD]",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "sep_token": {
24
- "content": "[SEP]",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "unk_token": {
31
- "content": "[UNK]",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false
36
- }
37
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
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
- "1": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": true
18
  },
19
- "2": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "3": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
@@ -32,7 +32,7 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "4": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
@@ -46,19 +46,12 @@
46
  "do_basic_tokenize": true,
47
  "do_lower_case": false,
48
  "mask_token": "[MASK]",
49
- "max_length": 512,
50
- "model_max_length": 2048,
51
  "never_split": null,
52
- "pad_to_multiple_of": null,
53
  "pad_token": "[PAD]",
54
- "pad_token_type_id": 0,
55
- "padding_side": "right",
56
  "sep_token": "[SEP]",
57
- "stride": 0,
58
  "strip_accents": null,
59
  "tokenize_chinese_chars": true,
60
  "tokenizer_class": "BertTokenizer",
61
- "truncation_side": "right",
62
- "truncation_strategy": "longest_first",
63
  "unk_token": "[UNK]"
64
  }
 
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,
 
46
  "do_basic_tokenize": true,
47
  "do_lower_case": false,
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,
54
  "tokenize_chinese_chars": true,
55
  "tokenizer_class": "BertTokenizer",
 
 
56
  "unk_token": "[UNK]"
57
  }
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff