Models:
Catherine Stones
cathy-stones/
Medical-NER
0
Downloads: 1
[047299]: / tokenizer_config.json

Download this file

59 lines (58 with data), 1.3 kB 

 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
{

  "added_tokens_decoder": {

    "0": {

      "content": "[PAD]",

      "lstrip": false,

      "normalized": false,

      "rstrip": false,

      "single_word": false,

      "special": true

    },

    "1": {

      "content": "[CLS]",

      "lstrip": false,

      "normalized": false,

      "rstrip": false,

      "single_word": false,

      "special": true

    },

    "2": {

      "content": "[SEP]",

      "lstrip": false,

      "normalized": false,

      "rstrip": false,

      "single_word": false,

      "special": true

    },

    "3": {

      "content": "[UNK]",

      "lstrip": false,

      "normalized": true,

      "rstrip": false,

      "single_word": false,

      "special": true

    },

    "128000": {

      "content": "[MASK]",

      "lstrip": false,

      "normalized": false,

      "rstrip": false,

      "single_word": false,

      "special": true

    }

  },

  "bos_token": "[CLS]",

  "clean_up_tokenization_spaces": true,

  "cls_token": "[CLS]",

  "do_lower_case": false,

  "eos_token": "[SEP]",

  "mask_token": "[MASK]",

  "model_max_length": 1000000000000000019884624838656,

  "pad_token": "[PAD]",

  "sep_token": "[SEP]",

  "sp_model_kwargs": {},

  "split_by_punct": false,

  "tokenizer_class": "DebertaV2Tokenizer",

  "unk_token": "[UNK]",

  "vocab_type": "spm"

}