pinzhenchen commited on
Commit
d0cf4ac
1 Parent(s): 7052ffa

Upload tokenizer_config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +12 -0
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "eos_token": "</s>",
4
+ "model_max_length": 512,
5
+ "pad_token": "<pad>",
6
+ "separate_vocabs": false,
7
+ "source_lang": "tmp",
8
+ "sp_model_kwargs": {},
9
+ "target_lang": "marian",
10
+ "tokenizer_class": "MarianTokenizer",
11
+ "unk_token": "<unk>"
12
+ }