Hugging Face's logo

adibm
/
sgd-opt-tokenizer

Model card Files
xet
Community
sgd-opt-tokenizer
File size: 2,078 Bytes 
cfb5c77
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
 
{
  "add_bos_token": true,
  "add_prefix_space": false,
  "additional_special_tokens": [
    "<|begintarget|>",
    "<|endtarget|>",
    "<|begincontext|>",
    "<|endcontext|>",
    "<|system|>",
    "<|user|>",
    "<|beginlastuserutterance|>",
    "<|endlastuserutterance|>",
    "<|begindsts|>",
    "<|enddsts|>",
    "<|begindst|>",
    "<|enddst|>",
    "<|beginbelief|>",
    "<|endbelief|>",
    "<|beginresponse|>",
    "<|endresponse|>",
    "<|beginaction|>",
    "<|endaction|>",
    "<|beginuseraction|>",
    "<|enduseraction|>",
    "<|sysactions|>",
    "<|beginintent|>",
    "<|endintent|>",
    "<|beginrequestedslots|>",
    "<|endrequestedslots|>",
    "<|promptdst|>",
    "<|promptaction|>",
    "<|promptresponse|>",
    "<|pad|>",
    "<|endoftext|>",
    "<|startoftext|>",
    "<|beginschema|>",
    "<|endschema|>",
    "<|schemaname|>",
    "<|schemadescription|>",
    "<|beginschemaintent|>",
    "<|endschemaintent|>",
    "<|intentrequiredslots|>",
    "<|intentresultslots|>",
    "<|intentoptionalslots|>",
    "<|possiblevalues|>",
    "<|endpossiblevalues|>",
    "<|beginschemaslot|>",
    "<|endschemaslot|>",
    "<|schemaslotvalues|>",
    "<|beginserviceresults|>",
    "<|endserviceresults|>"
  ],
  "bos_token": {
    "__type": "AddedToken",
    "content": "<|startoftext|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "clean_up_tokenization_spaces": true,
  "eos_token": {
    "__type": "AddedToken",
    "content": "<|endtarget|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "errors": "replace",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": {
    "__type": "AddedToken",
    "content": "<|pad|>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": {
    "__type": "AddedToken",
    "content": "</s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  }
}