eric0009 commited on
Commit
171544a
·
verified ·
1 Parent(s): 15ac88b

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +15 -0
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|startoftext|>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<|endoftext|>",
6
+ "fast": true,
7
+ "is_local": false,
8
+ "legacy": true,
9
+ "model_max_length": 4096,
10
+ "pad_token": "<|endoftext|>",
11
+ "sp_model_kwargs": {},
12
+ "tokenizer_class": "TokenizersBackend",
13
+ "unk_token": "<unk>",
14
+ "use_default_system_prompt": true
15
+ }