snoop2head commited on
Commit
913265d
1 Parent(s): 9d84280

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<cls>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "<sep>",
8
+ "unk_token": "<unk>"
9
+ }
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
+ "model_max_length": 512,
3
+ "special_tokens": [
4
+ "<s>",
5
+ "<pad>",
6
+ "</s>",
7
+ "<unk>",
8
+ "<cls>",
9
+ "<sep>",
10
+ "<mask>"
11
+ ],
12
+ "tokenizer_class": "PreTrainedTokenizerFast"
13
+ }