File size: 1,459 Bytes
e0f9624
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "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,
  "errors": "replace",
  "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"
  },
  "max_len": 512,
  "special_tokens_map_file": null,
  "name_or_path": "/gpfs/projects/bsc88/tools/corpus-utils-lm/17-06-2021-python/output/bne_es_output/roberta-2021-06-17-1849-3a6a-9c4f/train_tokenizer_output/train-tokenizer-2021-06-17-2216-3a6a-3cd6"
}