ryo0634 commited on
Commit
41016a8
1 Parent(s): f2dd229

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +7 -0
  2. tokenizer_config.json +21 -0
  3. vocab.txt +0 -0
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "do_subword_tokenize": true,
6
+ "do_word_tokenize": true,
7
+ "jumanpp_kwargs": null,
8
+ "mask_token": "[MASK]",
9
+ "mecab_kwargs": {
10
+ "mecab_dic": "unidic_lite"
11
+ },
12
+ "model_max_length": 512,
13
+ "never_split": null,
14
+ "pad_token": "[PAD]",
15
+ "sep_token": "[SEP]",
16
+ "subword_tokenizer_type": "wordpiece",
17
+ "sudachi_kwargs": null,
18
+ "tokenizer_class": "BertJapaneseTokenizer",
19
+ "unk_token": "[UNK]",
20
+ "word_tokenizer_type": "mecab"
21
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff