RichardErkhov commited on
Commit
60426a1
1 Parent(s): 4a396c5

uploaded model

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +80 -0
tokenizer_config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "65": {
28
+ "content": "[CLS]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "66": {
36
+ "content": "[SEP]",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "67": {
44
+ "content": "[MASK]",
45
+ "lstrip": true,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "105": {
52
+ "content": "<unk>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [],
61
+ "bos_token": "<s>",
62
+ "clean_up_tokenization_spaces": true,
63
+ "cls_token": "[CLS]",
64
+ "eos_token": "</s>",
65
+ "mask_token": "[MASK]",
66
+ "mask_token_sent": null,
67
+ "max_length": 256,
68
+ "model_max_length": 4096,
69
+ "offset": 0,
70
+ "pad_to_multiple_of": null,
71
+ "pad_token": "<pad>",
72
+ "pad_token_type_id": 0,
73
+ "padding_side": "right",
74
+ "sep_token": "[SEP]",
75
+ "stride": 0,
76
+ "tokenizer_class": "PegasusTokenizer",
77
+ "truncation_side": "right",
78
+ "truncation_strategy": "longest_first",
79
+ "unk_token": "<unk>"
80
+ }