ibraheemmoosa commited on
Commit
cefdda3
1 Parent(s): 57ceb87

Fix tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +15 -1
  2. tokenizer_config.json +19 -1
special_tokens_map.json CHANGED
@@ -1 +1,15 @@
1
- {}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<cls>",
3
+ "cls_token": "<cls>",
4
+ "eos_token": "<sep>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "<sep>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer_config.json CHANGED
@@ -1,3 +1,21 @@
1
  {
2
- "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  }
 
1
  {
2
+ "bos_token": "<cls>",
3
+ "cls_token": "<cls>",
4
+ "do_lower_case": true,
5
+ "eos_token": "<sep>",
6
+ "keep_accents": false,
7
+ "mask_token": {
8
+ "__type": "AddedToken",
9
+ "content": "<mask>",
10
+ "lstrip": true,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "model_max_length": 512,
16
+ "pad_token": "<pad>",
17
+ "remove_space": true,
18
+ "sep_token": "<sep>",
19
+ "tokenizer_class": "RemBertTokenizer",
20
+ "unk_token": "<unk>"
21
  }