tgsc commited on
Commit
1d44361
·
1 Parent(s): 42910ae

Upload 3 files

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|beginoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|pad|>",
5
+ "unk_token": "<|unk|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "model_max_length": 2048,
4
+ "special_tokens": [
5
+ "<|pad|>",
6
+ "<|endoftext|>",
7
+ "<|beginoftext|>",
8
+ "<|unk|>"
9
+ ],
10
+ "tokenizer_class": "PreTrainedTokenizerFast"
11
+ }