khaoulaoub commited on
Commit
93d6b1b
1 Parent(s): d499687

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +6 -0
  2. tokenizer_config.json +35 -0
  3. vocab.json +32 -34
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 34,
3
+ "<s>": 33,
4
+ "[PAD]": 32,
5
+ "[UNK]": 31
6
+ }
tokenizer_config.json CHANGED
@@ -1,4 +1,39 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": "<s>",
3
  "clean_up_tokenization_spaces": true,
4
  "do_lower_case": false,
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "31": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "32": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "33": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "34": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "additional_special_tokens": [],
37
  "bos_token": "<s>",
38
  "clean_up_tokenization_spaces": true,
39
  "do_lower_case": false,
vocab.json CHANGED
@@ -1,37 +1,35 @@
1
  {
2
- "[PAD]": 34,
3
- "[UNK]": 33,
4
- "|": 20,
5
- "ء": 19,
6
  "ا": 6,
7
- "ب": 1,
8
- "ة": 24,
9
- "ت": 10,
10
- "ث": 9,
11
- "ج": 25,
12
- "ح": 31,
13
- "خ": 11,
14
- "د": 29,
15
- "ذ": 15,
16
- "ر": 27,
17
- "ز": 8,
18
- "س": 21,
19
- "ش": 5,
20
- "ص": 3,
21
- "ض": 14,
22
- "ط": 16,
23
- "ظ": 13,
24
- "ع": 26,
25
- "غ": 22,
26
- "ـ": 12,
27
- "ف": 23,
28
- "ق": 32,
29
- "ك": 7,
30
- "ل": 18,
31
- "م": 0,
32
- "ن": 2,
33
- "ه": 28,
34
- "و": 30,
35
- "ى": 4,
36
- "ي": 17
37
  }
 
1
  {
2
+ "[PAD]": 32,
3
+ "[UNK]": 31,
4
+ "|": 18,
5
+ "ء": 12,
6
  "ا": 6,
7
+ "ب": 24,
8
+ "ة": 11,
9
+ "ت": 8,
10
+ "ث": 30,
11
+ "ج": 26,
12
+ "ح": 19,
13
+ "خ": 14,
14
+ "د": 28,
15
+ "ذ": 23,
16
+ "ر": 17,
17
+ "ز": 0,
18
+ "س": 10,
19
+ "ش": 25,
20
+ "ص": 21,
21
+ "ض": 1,
22
+ "ط": 2,
23
+ "ظ": 4,
24
+ "ع": 16,
25
+ "غ": 9,
26
+ "ف": 22,
27
+ "ق": 27,
28
+ "ك": 29,
29
+ "ل": 13,
30
+ "م": 20,
31
+ "ن": 5,
32
+ "ه": 3,
33
+ "و": 15,
34
+ "ي": 7
 
 
35
  }