Kanit commited on
Commit
41d3a5a
1 Parent(s): 5dbd4d0

Upload tokenizer

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +5 -3
tokenizer_config.json CHANGED
@@ -1,12 +1,14 @@
1
  {
 
 
2
  "cls_token": "[CLS]",
 
3
  "do_lower_case": true,
4
  "mask_token": "[MASK]",
5
- "model_max_length": 512,
6
- "name_or_path": "bert-base-uncased",
7
  "pad_token": "[PAD]",
8
  "sep_token": "[SEP]",
9
- "special_tokens_map_file": null,
10
  "strip_accents": null,
11
  "tokenize_chinese_chars": true,
12
  "tokenizer_class": "BertTokenizer",
 
1
  {
2
+ "add_prefix_space": true,
3
+ "clean_up_tokenization_spaces": true,
4
  "cls_token": "[CLS]",
5
+ "do_basic_tokenize": true,
6
  "do_lower_case": true,
7
  "mask_token": "[MASK]",
8
+ "model_max_length": 1000000000000000019884624838656,
9
+ "never_split": null,
10
  "pad_token": "[PAD]",
11
  "sep_token": "[SEP]",
 
12
  "strip_accents": null,
13
  "tokenize_chinese_chars": true,
14
  "tokenizer_class": "BertTokenizer",