anuml commited on
Commit
95b640a
·
verified ·
1 Parent(s): 7e8d845

upload: tokenizer/tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer/tokenizer_config.json +15 -0
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|bos|>",
4
+ "eos_token": "<|eos|>",
5
+ "extra_special_tokens": [
6
+ "<|trans|>",
7
+ "<|vi|>",
8
+ "<|ja|>",
9
+ "<|en|>"
10
+ ],
11
+ "model_max_length": 1000000000000000019884624838656,
12
+ "pad_token": "<|pad|>",
13
+ "tokenizer_class": "TokenizersBackend",
14
+ "unk_token": "<|unk|>"
15
+ }