File size: 1,477 Bytes
5342a88
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
    "errors": "replace",
    "unk_token": {
        "content": "<unk>",
        "single_word": false,
        "lstrip": false,
        "rstrip": false,
        "normalized": true,
        "__type": "AddedToken"
    },
    "bos_token": {
        "content": "<s>",
        "single_word": false,
        "lstrip": false,
        "rstrip": false,
        "normalized": true,
        "__type": "AddedToken"
    },
    "eos_token": {
        "content": "</s>",
        "single_word": false,
        "lstrip": false,
        "rstrip": false,
        "normalized": true,
        "__type": "AddedToken"
    },
    "add_prefix_space": false,
    "sep_token": {
        "content": "</s>",
        "single_word": false,
        "lstrip": false,
        "rstrip": false,
        "normalized": true,
        "__type": "AddedToken"
    },
    "cls_token": {
        "content": "<s>",
        "single_word": false,
        "lstrip": false,
        "rstrip": false,
        "normalized": true,
        "__type": "AddedToken"
    },
    "pad_token": {
        "content": "<pad>",
        "single_word": false,
        "lstrip": false,
        "rstrip": false,
        "normalized": true,
        "__type": "AddedToken"
    },
    "mask_token": {
        "content": "<mask>",
        "single_word": false,
        "lstrip": true,
        "rstrip": false,
        "normalized": true,
        "__type": "AddedToken"
    },
    "model_max_length": 512,
    "tokenizer_class": "RobertaTokenizer"
}