yuewang-sf commited on
Commit
aa01b14
1 Parent(s): 7317944

Upload tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +62 -1
tokenizer_config.json CHANGED
@@ -1 +1,62 @@
1
- {"errors": "replace", "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "tokenizer_class": "RobertaTokenizer"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "errors": "replace",
3
+ "unk_token": {
4
+ "content": "<unk>",
5
+ "single_word": false,
6
+ "lstrip": false,
7
+ "rstrip": false,
8
+ "normalized": true,
9
+ "__type": "AddedToken"
10
+ },
11
+ "bos_token": {
12
+ "content": "<s>",
13
+ "single_word": false,
14
+ "lstrip": false,
15
+ "rstrip": false,
16
+ "normalized": true,
17
+ "__type": "AddedToken"
18
+ },
19
+ "eos_token": {
20
+ "content": "</s>",
21
+ "single_word": false,
22
+ "lstrip": false,
23
+ "rstrip": false,
24
+ "normalized": true,
25
+ "__type": "AddedToken"
26
+ },
27
+ "add_prefix_space": false,
28
+ "sep_token": {
29
+ "content": "</s>",
30
+ "single_word": false,
31
+ "lstrip": false,
32
+ "rstrip": false,
33
+ "normalized": true,
34
+ "__type": "AddedToken"
35
+ },
36
+ "cls_token": {
37
+ "content": "<s>",
38
+ "single_word": false,
39
+ "lstrip": false,
40
+ "rstrip": false,
41
+ "normalized": true,
42
+ "__type": "AddedToken"
43
+ },
44
+ "pad_token": {
45
+ "content": "<pad>",
46
+ "single_word": false,
47
+ "lstrip": false,
48
+ "rstrip": false,
49
+ "normalized": true,
50
+ "__type": "AddedToken"
51
+ },
52
+ "mask_token": {
53
+ "content": "<mask>",
54
+ "single_word": false,
55
+ "lstrip": true,
56
+ "rstrip": false,
57
+ "normalized": true,
58
+ "__type": "AddedToken"
59
+ },
60
+ "model_max_length": 512,
61
+ "tokenizer_class": "RobertaTokenizer"
62
+ }