Rafaelvariavel commited on
Commit
a3882e5
·
verified ·
1 Parent(s): 2a99d0b

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +9 -0
tokenizer_config.json CHANGED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>",
6
+ "tokenizer_class": "GPT2Tokenizer",
7
+ "clean_up_tokenization_spaces": true,
8
+ "model_max_length": 1024
9
+ }