File size: 1,781 Bytes
08cf483
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 24,
      "content": "[UNK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 25,
      "content": "[PAD]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 26,
      "content": "[MASK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 27,
      "content": "[SEP]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 28,
      "content": "[CLS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": []
  },
  "pre_tokenizer": {
    "type": "WhitespaceSplit"
  },
  "post_processor": null,
  "decoder": {
    "type": "WordPiece",
    "prefix": "##",
    "cleanup": true
  },
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<boc>": 0,
      "<eoc>": 1,
      "<sepc>": 2,
      "<bog>": 3,
      "<eog>": 4,
      "<sepg>": 5,
      "IDX_0": 6,
      "IDX_1": 7,
      "IDX_2": 8,
      "IDX_3": 9,
      "IDX_4": 10,
      "IDX_5": 11,
      "IDX_6": 12,
      "IDX_7": 13,
      "IDX_8": 14,
      "IDX_9": 15,
      "ATOM_C": 16,
      "ATOM_N": 17,
      "ATOM_O": 18,
      "ATOM_F": 19,
      "BOND_SINGLE": 20,
      "BOND_DOUBLE": 21,
      "BOND_TRIPLE": 22,
      "BOND_AROMATIC": 23
    },
    "unk_token": "[UNK]"
  }
}