Llamarider222 commited on
Commit
95eb66e
1 Parent(s): 6c568ae

Upload tokenizer

Browse files
special_tokens_map.json CHANGED
@@ -13,7 +13,7 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<unk>",
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "</s>",
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
tokenizer.json CHANGED
@@ -9,7 +9,7 @@
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
- "normalized": true,
13
  "special": true
14
  },
15
  {
@@ -29,6 +29,15 @@
29
  "rstrip": false,
30
  "normalized": true,
31
  "special": true
 
 
 
 
 
 
 
 
 
32
  }
33
  ],
34
  "normalizer": {
 
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
+ "normalized": false,
13
  "special": true
14
  },
15
  {
 
29
  "rstrip": false,
30
  "normalized": true,
31
  "special": true
32
+ },
33
+ {
34
+ "id": 32000,
35
+ "content": "<pad>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": true,
40
+ "special": false
41
  }
42
  ],
43
  "normalizer": {
tokenizer_config.json CHANGED
@@ -1,6 +1,4 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
  "bos_token": {
5
  "__type": "AddedToken",
6
  "content": "<s>",
 
1
  {
 
 
2
  "bos_token": {
3
  "__type": "AddedToken",
4
  "content": "<s>",