File size: 1,416 Bytes
faecb10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
    "add_prefix_space": false,
    "added_tokens_decoder": {
      "0": {
        "content": "[BOS]",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      },
      "1": {
        "content": "[PAD]",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      },
      "2": {
        "content": "[CLS]",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      },
      "3": {
        "content": "[MASK]",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      },
      "6": {
        "content": "[UNK]",
        "lstrip": false,
        "normalized": false,
        "rstrip": false,
        "single_word": false,
        "special": true
      }
    },
    "bos_token": "[BOS]",
    "characters": [
      "A",
      "C",
      "G",
      "U",
      "N",
      "E",
      "T"
    ],
    "clean_up_tokenization_spaces": false,
    "cls_token": "[CLS]",
    "eos_token": "[SEP]",
    "mask_token": "[MASK]",
    "model_max_length": 12288,
    "pad_token": "[PAD]",
    "padding_side": "left",
    "sep_token": "[SEP]",
    "tokenizer_class": "CharTokenizer",
    "unk_token": "[UNK]"
  }