shunxing1234 commited on
Commit
351d4a6
1 Parent(s): bda0103

Upload tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +10 -0
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 2048,
7
+ "padding_side": "right",
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }