Hugging Face's logo

okbenzene2002
/
english-tokenizer

Transformers
Inference Endpoints
Model card Files Community
okbenzene2002 commited on
Commit
3d5893d
•
1 Parent(s): 6f27822

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +35 -37
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +5 -7
special_tokens_map.json CHANGED
@@ -1,39 +1,37 @@
1
  {
2
- "additional_special_tokens": [
3
- {
4
- "content": "[PAD]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- {
11
- "content": "[UNK]",
12
- "lstrip": false,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
- },
17
- {
18
- "content": "[CLS]",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
- {
25
- "content": "[SEP]",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- },
31
- {
32
- "content": "[MASK]",
33
- "lstrip": false,
34
- "normalized": false,
35
- "rstrip": false,
36
- "single_word": false
37
- }
38
- ]
39
  }
 
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
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -41,15 +41,13 @@
41
  "special": true
42
  }
43
  },
44
- "additional_special_tokens": [
45
- "[PAD]",
46
- "[UNK]",
47
- "[CLS]",
48
- "[SEP]",
49
- "[MASK]"
50
- ],
51
  "clean_up_tokenization_spaces": true,
 
 
52
  "model_max_length": 1000000000000000019884624838656,
 
 
53
  "tokenizer_class": "PreTrainedTokenizerFast",
 
54
  "use_fast": true
55
  }
 
41
  "special": true
42
  }
43
  },
 
 
 
 
 
 
 
44
  "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "mask_token": "[MASK]",
47
  "model_max_length": 1000000000000000019884624838656,
48
+ "pad_token": "[PAD]",
49
+ "sep_token": "[SEP]",
50
  "tokenizer_class": "PreTrainedTokenizerFast",
51
+ "unk_token": "[UNK]",
52
  "use_fast": true
53
  }