BrightXiaoHan commited on
Commit
49bdfe5
1 Parent(s): 4634d4f

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +11 -0
  2. tokenizer_config.json +19 -0
  3. vocab.txt +0 -0
special_tokens_map.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<mask_1>"
4
+ ],
5
+ "cls_token": "[CLS]",
6
+ "eos_token": "</s>",
7
+ "mask_token": "<mask_2>",
8
+ "pad_token": "<pad>",
9
+ "sep_token": "[SEP]",
10
+ "unk_token": "<unk>"
11
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<mask_1>"
4
+ ],
5
+ "clean_up_tokenization_spaces": true,
6
+ "cls_token": "[CLS]",
7
+ "do_basic_tokenize": true,
8
+ "do_lower_case": true,
9
+ "eos_token": "</s>",
10
+ "mask_token": "<mask_2>",
11
+ "model_max_length": 1000000000000000019884624838656,
12
+ "never_split": null,
13
+ "pad_token": "<pad>",
14
+ "sep_token": "[SEP]",
15
+ "strip_accents": null,
16
+ "tokenize_chinese_chars": true,
17
+ "tokenizer_class": "PegasusTokenizer",
18
+ "unk_token": "<unk>"
19
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff