kimsan0622 commited on
Commit
a584a43
1 Parent(s): da5de43

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "!",
3
+ "cls_token": "&",
4
+ "eos_token": "\"",
5
+ "mask_token": "'",
6
+ "pad_token": "%",
7
+ "sep_token": "$",
8
+ "unk_token": "#"
9
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "name_or_path": "vocab/ko_en_44000/ko20000_ByteLevelBPETokenizer",
3
+ "special_tokens": [
4
+ "<s>",
5
+ "</s>",
6
+ "<unk>",
7
+ "<sep>",
8
+ "<pad>",
9
+ "<cls>",
10
+ "<mask>"
11
+ ],
12
+ "special_tokens_map_file": "vocab/ko_en_44000/ko20000_ByteLevelBPETokenizer/special_tokens_map.json",
13
+ "tokenizer_class": "PreTrainedTokenizerFast"
14
+ }