Hugging Face's logo

dotan1111
/
BioTokenizer-BFD-WPC-100

biology
bioinformatics
tokenizers
Model card Files Community
BioTokenizer-BFD-WPC-100
File size: 2,265 Bytes 
7ea4c5e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
 
{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<UNK>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Lowercase"
  },
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordPiece",
    "unk_token": "<UNK>",
    "continuing_subword_prefix": "##",
    "max_input_chars_per_word": 10000,
    "vocab": {
      "<UNK>": 0,
      "a": 1,
      "b": 2,
      "c": 3,
      "d": 4,
      "e": 5,
      "f": 6,
      "g": 7,
      "h": 8,
      "i": 9,
      "k": 10,
      "l": 11,
      "m": 12,
      "n": 13,
      "o": 14,
      "p": 15,
      "q": 16,
      "r": 17,
      "s": 18,
      "t": 19,
      "u": 20,
      "v": 21,
      "w": 22,
      "x": 23,
      "y": 24,
      "z": 25,
      "##h": 26,
      "##g": 27,
      "##k": 28,
      "##s": 29,
      "##t": 30,
      "##e": 31,
      "##a": 32,
      "##w": 33,
      "##l": 34,
      "##n": 35,
      "##v": 36,
      "##r": 37,
      "##p": 38,
      "##i": 39,
      "##q": 40,
      "##f": 41,
      "##d": 42,
      "##m": 43,
      "##y": 44,
      "##x": 45,
      "##c": 46,
      "##z": 47,
      "##u": 48,
      "##o": 49,
      "##b": 50,
      "##aa": 51,
      "##ll": 52,
      "##la": 53,
      "##gg": 54,
      "##rr": 55,
      "##va": 56,
      "##ga": 57,
      "##ra": 58,
      "##lv": 59,
      "##pa": 60,
      "##lg": 61,
      "##sa": 62,
      "##lr": 63,
      "##ea": 64,
      "##vv": 65,
      "##da": 66,
      "##ta": 67,
      "##ls": 68,
      "##lp": 69,
      "##ia": 70,
      "##ld": 71,
      "##gr": 72,
      "##le": 73,
      "##ss": 74,
      "##gv": 75,
      "##lt": 76,
      "##gs": 77,
      "##er": 78,
      "##gt": 79,
      "##gd": 80,
      "##li": 81,
      "##pp": 82,
      "##vr": 83,
      "##ge": 84,
      "##qa": 85,
      "##fa": 86,
      "##lk": 87,
      "##vt": 88,
      "##vs": 89,
      "##gi": 90,
      "##vd": 91,
      "##ve": 92,
      "##lf": 93,
      "##pr": 94,
      "##ka": 95,
      "##dr": 96,
      "##lq": 97,
      "##ps": 98,
      "##ee": 99
    }
  }
}