shunxing1234 commited on
Commit
a969743
1 Parent(s): 564f27b

Upload 4 files

Browse files
Files changed (4) hide show
  1. merges.txt +0 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +9 -0
  4. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 2048,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff