nagupv commited on
Commit
3ce00df
1 Parent(s): 368275d

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +9 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +17 -0
  4. vocab.txt +0 -0
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<cls>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "<sep>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_text": true,
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<cls>",
6
+ "do_lower_case": true,
7
+ "eos_token": "</s>",
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 512,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "<sep>",
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "FunnelTokenizer",
15
+ "unk_token": "<unk>",
16
+ "wordpieces_prefix": "##"
17
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff