aakashMeghwar01 commited on
Commit
59c2a98
·
verified ·
1 Parent(s): 9f10a26

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +20 -0
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "is_local": true,
4
+ "max_length": 512,
5
+ "model_max_length": 512,
6
+ "pad_to_multiple_of": null,
7
+ "pad_token": "<|pad|>",
8
+ "pad_token_type_id": 0,
9
+ "padding_side": "right",
10
+ "special_tokens": {
11
+ "eos": "<|endoftext|>",
12
+ "pad": "<|pad|>",
13
+ "unk": "<|unk|>"
14
+ },
15
+ "stride": 0,
16
+ "tokenizer_class": "TokenizersBackend",
17
+ "truncation_side": "right",
18
+ "truncation_strategy": "longest_first",
19
+ "vocab_size": 24000
20
+ }