powidla commited on
Commit
7ccb860
·
verified ·
1 Parent(s): c107ba0

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +13 -0
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|begin▁of▁sentence|>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<|end▁of▁sentence|>",
6
+ "is_local": false,
7
+ "legacy": true,
8
+ "model_max_length": 16384,
9
+ "pad_token": "<|end▁of▁sentence|>",
10
+ "sp_model_kwargs": {},
11
+ "tokenizer_class": "TokenizersBackend",
12
+ "unk_token": null
13
+ }