Hoglet-33 commited on
Commit
6685b3a
·
verified ·
1 Parent(s): 59a409e

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +15 -0
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|end_of_text|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|end_of_text|>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "model_max_length": 1000000000000000019884624838656,
10
+ "model_specific_special_tokens": {},
11
+ "pad_token": "<|end_of_text|>",
12
+ "padding_side": "right",
13
+ "tokenizer_class": "GPT2Tokenizer",
14
+ "unk_token": "<|unk|>"
15
+ }