mathieu commited on
Commit
ed67012
1 Parent(s): 77e8cc0

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +15 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +22 -0
  4. vocab.txt +0 -0
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "[UNK]"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "do_lower_case": true,
6
+ "eos_token": "</s>",
7
+ "mask_token": "<mask>",
8
+ "max_length": 384,
9
+ "model_max_length": 512,
10
+ "pad_to_multiple_of": null,
11
+ "pad_token": "<pad>",
12
+ "pad_token_type_id": 0,
13
+ "padding_side": "right",
14
+ "sep_token": "</s>",
15
+ "stride": 0,
16
+ "strip_accents": null,
17
+ "tokenize_chinese_chars": true,
18
+ "tokenizer_class": "MPNetTokenizer",
19
+ "truncation_side": "right",
20
+ "truncation_strategy": "longest_first",
21
+ "unk_token": "[UNK]"
22
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff