abehandler commited on
Commit
88ec98d
·
verified ·
1 Parent(s): 08e1f1d

Upload tokenizer

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