deepakm10 commited on
Commit
8b5e734
·
verified ·
1 Parent(s): 213e592

Upload roberta_stage2/tokenizer_config.json with huggingface_hub

Browse files
roberta_stage2/tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "is_local": true,
9
+ "mask_token": "<mask>",
10
+ "max_length": 96,
11
+ "model_max_length": 512,
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "stride": 0,
15
+ "tokenizer_class": "RobertaTokenizer",
16
+ "trim_offsets": true,
17
+ "truncation_side": "right",
18
+ "truncation_strategy": "longest_first",
19
+ "unk_token": "<unk>"
20
+ }