rodrigo-nogueira commited on
Commit
ee9a02b
1 Parent(s): 2af887a

Upload 2 files

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_bos_token": false,
3
+ "add_eos_token": false,
4
+ "model_max_length": 4096,
5
+ "unk_token": "<unk>",
6
+ "bos_token": "<|startoftext|>",
7
+ "eos_token": "<|endoftext|>",
8
+ "pad_token": "<unk>",
9
+ "sp_model_kwargs": {},
10
+ "clean_up_tokenization_spaces": false,
11
+ "legacy": true,
12
+ "tokenizer_class": "LlamaTokenizer"
13
+ }