yuka-04 commited on
Commit
a127f36
·
verified ·
1 Parent(s): a7b53f9

delete file

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +0 -63
tokenizer_config.json DELETED
@@ -1,63 +0,0 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "[PAD]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "4": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
- "clean_up_tokenization_spaces": true,
45
- "cls_token": "[CLS]",
46
- "do_lower_case": false,
47
- "do_subword_tokenize": true,
48
- "do_word_tokenize": true,
49
- "jumanpp_kwargs": null,
50
- "mask_token": "[MASK]",
51
- "mecab_kwargs": {
52
- "mecab_option": "data/MANBYO_201907_Dic-utf8.dic"
53
- },
54
- "model_max_length": 1000000000000000019884624838656,
55
- "never_split": null,
56
- "pad_token": "[PAD]",
57
- "sep_token": "[SEP]",
58
- "subword_tokenizer_type": "wordpiece",
59
- "sudachi_kwargs": null,
60
- "tokenizer_class": "BertJapaneseTokenizer",
61
- "unk_token": "[UNK]",
62
- "word_tokenizer_type": "mecab"
63
- }