melissasanabria commited on
Commit
5e45af8
1 Parent(s): 9513732

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +4 -1
  2. tokenizer_config.json +10 -2
special_tokens_map.json CHANGED
@@ -1 +1,4 @@
1
- {}
 
 
 
 
1
+ {
2
+ "mask_token": "[MASK]",
3
+ "pad_token": "[PAD]"
4
+ }
tokenizer_config.json CHANGED
@@ -1,5 +1,13 @@
1
  {
2
  "clean_up_tokenization_spaces": true,
3
- "model_max_length": 1000000000000000019884624838656,
4
- "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
 
 
 
 
 
5
  }
 
1
  {
2
  "clean_up_tokenization_spaces": true,
3
+ "do_lower_case": false,
4
+ "model_max_length": 512,
5
+ "special_tokens": {
6
+ "mask_token": "[MASK]",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]"
9
+ },
10
+ "tokenize_chinese_chars": false,
11
+ "tokenizer_class": "PreTrainedTokenizerFast",
12
+ "trust_remote_code": true
13
  }