nobu-g commited on
Commit
dd003f5
1 Parent(s): e82a1b8

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +16 -1
tokenizer_config.json CHANGED
@@ -1 +1,16 @@
1
- {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "do_lower_case": false, "do_word_tokenize": true, "do_subword_tokenize": true, "word_tokenizer_type": "basic", "subword_tokenizer_type": "character", "never_split": null, "mecab_kwargs": null, "special_tokens_map_file": null, "name_or_path": "data/japanese_bert_tokenizer", "tokenizer_class": "BertJapaneseTokenizer"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "unk_token": "[UNK]",
3
+ "sep_token": "[SEP]",
4
+ "pad_token": "[PAD]",
5
+ "cls_token": "[CLS]",
6
+ "mask_token": "[MASK]",
7
+ "do_lower_case": false,
8
+ "do_word_tokenize": true,
9
+ "do_subword_tokenize": true,
10
+ "word_tokenizer_type": "basic",
11
+ "subword_tokenizer_type": "character",
12
+ "never_split": null,
13
+ "mecab_kwargs": null,
14
+ "special_tokens_map_file": null,
15
+ "tokenizer_class": "BertJapaneseTokenizer"
16
+ }