File size: 1,260 Bytes
be8b88a
912f828
be8b88a
 
912f828
be8b88a
912f828
be8b88a
 
 
 
912f828
 
be8b88a
912f828
be8b88a
 
 
 
912f828
 
be8b88a
912f828
be8b88a
 
 
 
912f828
 
be8b88a
912f828
be8b88a
 
 
 
912f828
 
 
be8b88a
 
 
 
 
 
912f828
be8b88a
912f828
 
 
be8b88a
912f828
 
be8b88a
912f828
 
 
 
 
be8b88a
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
{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "<mask>",
      "lstrip": true,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": false,
  "cls_token": "<s>",
  "eos_token": "</s>",
  "errors": "replace",
  "extra_special_tokens": {},
  "mask_token": "<mask>",
  "max_len": 512,
  "model_max_length": 512,
  "pad_token": "<pad>",
  "sep_token": "</s>",
  "tokenizer_class": "RobertaTokenizer",
  "trim_offsets": true,
  "unk_token": "<unk>"
}