raygx commited on
Commit
8b49607
1 Parent(s): d42054b

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +5 -13
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +12 -16
  4. vocab.txt +0 -0
special_tokens_map.json CHANGED
@@ -1,15 +1,7 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
5
- "mask_token": {
6
- "content": "<mask>",
7
- "lstrip": true,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "pad_token": "<pad>",
13
- "sep_token": "</s>",
14
- "unk_token": "<unk>"
15
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
7
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,19 +1,15 @@
1
  {
2
- "bos_token": "<s>",
3
  "clean_up_tokenization_spaces": true,
4
- "cls_token": "<s>",
5
- "eos_token": "</s>",
6
- "mask_token": {
7
- "__type": "AddedToken",
8
- "content": "<mask>",
9
- "lstrip": true,
10
- "normalized": false,
11
- "rstrip": false,
12
- "single_word": false
13
- },
14
- "model_max_length": 512,
15
- "pad_token": "<pad>",
16
- "sep_token": "</s>",
17
- "tokenizer_class": "PreTrainedTokenizerFast",
18
- "unk_token": "<unk>"
19
  }
 
1
  {
 
2
  "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
 
 
 
15
  }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff