rippertnt commited on
Commit
7c2c933
1 Parent(s): 112e95c

add tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "mask_token": "<mask>",
5
+ "pad_token": "<pad>",
6
+ "unk_token": "<unk>"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "mask_token": "<mask>",
5
+ "pad_token": "<pad>",
6
+ "tokenizer_class": "PreTrainedTokenizerFast",
7
+ "unk_token": "<unk>"
8
+ }