Hugging Face's logo

ntuteama
/
NLP_tokeniser2

Transformers
Model card Files
xet
Community
ntuteama commited on
Commit
fa54fa3
·
verified ·
1 Parent(s): dfe7699

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +7 -7
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +12 -12
special_tokens_map.json CHANGED
@@ -1,7 +1,7 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
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
@@ -1,12 +1,12 @@
1
- {
2
- "added_tokens_decoder": {},
3
- "clean_up_tokenization_spaces": false,
4
- "cls_token": "[CLS]",
5
- "extra_special_tokens": {},
6
- "mask_token": "[MASK]",
7
- "model_max_length": 1000000000000000019884624838656,
8
- "pad_token": "[PAD]",
9
- "sep_token": "[SEP]",
10
- "tokenizer_class": "PreTrainedTokenizerFast",
11
- "unk_token": "[UNK]"
12
- }
 
1
+ {
2
+ "added_tokens_decoder": {},
3
+ "clean_up_tokenization_spaces": false,
4
+ "cls_token": "[CLS]",
5
+ "extra_special_tokens": {},
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "tokenizer_class": "PreTrainedTokenizerFast",
11
+ "unk_token": "[UNK]"
12
+ }