ml-ryanlee commited on
Commit
1193677
·
verified ·
1 Parent(s): ec995f3

Add gpt2 tokenizer: tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +12 -0
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "model_max_length": 1024,
9
+ "pad_token": null,
10
+ "tokenizer_class": "GPT2Tokenizer",
11
+ "unk_token": "<|endoftext|>"
12
+ }