saadMouraf commited on
Commit
ac93bd9
1 Parent(s): 36bc7f4

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +7 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +21 -0
  4. vocab.txt +0 -0
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "mask_token": "[MASK]",
7
+ "max_len": 512,
8
+ "model_max_length": 512,
9
+ "never_split": [
10
+ "[بريد]",
11
+ "[مستخدم]",
12
+ "[رابط]"
13
+ ],
14
+ "pad_token": "[PAD]",
15
+ "sep_token": "[SEP]",
16
+ "strip_accents": null,
17
+ "tokenize_chinese_chars": true,
18
+ "tokenizer_class": "BertTokenizer",
19
+ "unk_token": "[UNK]",
20
+ "use_fast": true
21
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff