ryo0634 commited on
Commit
b0c1dea
1 Parent(s): d4421db

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +7 -0
  2. tokenizer_config.json +22 -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 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": false,
4
+ "do_subword_tokenize": true,
5
+ "do_word_tokenize": true,
6
+ "jumanpp_kwargs": null,
7
+ "mask_token": "[MASK]",
8
+ "mecab_kwargs": {
9
+ "mecab_dic": "unidic_lite"
10
+ },
11
+ "model_max_length": 512,
12
+ "name_or_path": "results_marc_ja/bert-base-japanese-v3/lr_5e-05_epochs_3_seed_42",
13
+ "never_split": null,
14
+ "pad_token": "[PAD]",
15
+ "sep_token": "[SEP]",
16
+ "special_tokens_map_file": null,
17
+ "subword_tokenizer_type": "wordpiece",
18
+ "sudachi_kwargs": null,
19
+ "tokenizer_class": "BertJapaneseTokenizer",
20
+ "unk_token": "[UNK]",
21
+ "word_tokenizer_type": "mecab"
22
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff