nadika commited on
Commit
f493739
1 Parent(s): 2fed44e

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +35 -5
  2. tokenizer_config.json +7 -0
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
  }
tokenizer_config.json CHANGED
@@ -46,12 +46,19 @@
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,
54
  "tokenize_chinese_chars": true,
55
  "tokenizer_class": "BertTokenizer",
 
 
56
  "unk_token": "[UNK]"
57
  }
 
46
  "do_basic_tokenize": true,
47
  "do_lower_case": true,
48
  "mask_token": "[MASK]",
49
+ "max_length": 512,
50
  "model_max_length": 1000000000000000019884624838656,
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
  }