stefan-it commited on
Commit
262548b
1 Parent(s): 284d179

tokenizer: add initial configuration

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +17 -0
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_lower_case": false,
3
+ "bos_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "unk_token": "[UNK]",
6
+ "sep_token": "[SEP]",
7
+ "pad_token": "[PAD]",
8
+ "cls_token": "[CLS]",
9
+ "mask_token": "[MASK]",
10
+ "split_by_punct": false,
11
+ "special_tokens_map_file": null,
12
+ "name_or_path": "gwlms/deberta-base-dewiki-v1",
13
+ "sp_model_kwargs": {},
14
+ "tokenizer_file": null,
15
+ "tokenizer_class": "DebertaV2Tokenizer",
16
+ "vocab_type": "spm"
17
+ }