ychafiqui commited on
Commit
0caf9f2
·
1 Parent(s): fee0b05

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 +49 -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 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "full_tokenizer_file": null,
7
+ "mask_token": "[MASK]",
8
+ "max_len": 512,
9
+ "model_max_length": 512,
10
+ "never_split": [
11
+ "+وا",
12
+ "س+",
13
+ "[مستخدم]",
14
+ "+ك",
15
+ "+هم",
16
+ "+ة",
17
+ "+ن",
18
+ "لل+",
19
+ "[بريد]",
20
+ "[رابط]",
21
+ "+ه",
22
+ "+كن",
23
+ "+ا",
24
+ "+ات",
25
+ "+ي",
26
+ "ب+",
27
+ "+نا",
28
+ "+هن",
29
+ "+كم",
30
+ "ك+",
31
+ "+ين",
32
+ "+هما",
33
+ "و+",
34
+ "+كما",
35
+ "+ان",
36
+ "+ت",
37
+ "+ون",
38
+ "ل+",
39
+ "+ها",
40
+ "ال+",
41
+ "ف+"
42
+ ],
43
+ "pad_token": "[PAD]",
44
+ "sep_token": "[SEP]",
45
+ "strip_accents": null,
46
+ "tokenize_chinese_chars": true,
47
+ "tokenizer_class": "BertTokenizer",
48
+ "unk_token": "[UNK]"
49
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff