Padajno commited on
Commit
c4f37fb
·
verified ·
1 Parent(s): 9ee0c13

Upload tokenizer

Browse files
Files changed (3) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +1 -1
  3. vocab.txt +0 -0
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -49,7 +49,7 @@
49
  "model_max_length": 512,
50
  "pad_token": "[PAD]",
51
  "sep_token": "[SEP]",
52
- "strip_accents": null,
53
  "tokenize_chinese_chars": true,
54
  "tokenizer_class": "BertTokenizer",
55
  "unk_token": "[UNK]"
 
49
  "model_max_length": 512,
50
  "pad_token": "[PAD]",
51
  "sep_token": "[SEP]",
52
+ "strip_accents": false,
53
  "tokenize_chinese_chars": true,
54
  "tokenizer_class": "BertTokenizer",
55
  "unk_token": "[UNK]"
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff