oddadmix commited on
Commit
ee26880
·
verified ·
1 Parent(s): f353a54

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
@@ -71,16 +71,23 @@
71
  "do_lower_case": false,
72
  "mask_token": "[MASK]",
73
  "max_len": 512,
 
74
  "model_max_length": 512,
75
  "never_split": [
76
  "[بريد]",
77
  "[مستخدم]",
78
  "[رابط]"
79
  ],
 
80
  "pad_token": "[PAD]",
 
 
81
  "sep_token": "[SEP]",
 
82
  "strip_accents": null,
83
  "tokenize_chinese_chars": true,
84
  "tokenizer_class": "BertTokenizer",
 
 
85
  "unk_token": "[UNK]"
86
  }
 
71
  "do_lower_case": false,
72
  "mask_token": "[MASK]",
73
  "max_len": 512,
74
+ "max_length": 512,
75
  "model_max_length": 512,
76
  "never_split": [
77
  "[بريد]",
78
  "[مستخدم]",
79
  "[رابط]"
80
  ],
81
+ "pad_to_multiple_of": null,
82
  "pad_token": "[PAD]",
83
+ "pad_token_type_id": 0,
84
+ "padding_side": "right",
85
  "sep_token": "[SEP]",
86
+ "stride": 0,
87
  "strip_accents": null,
88
  "tokenize_chinese_chars": true,
89
  "tokenizer_class": "BertTokenizer",
90
+ "truncation_side": "right",
91
+ "truncation_strategy": "longest_first",
92
  "unk_token": "[UNK]"
93
  }