minseong commited on
Commit
f65d960
1 Parent(s): aa4a70b

add tokens

Browse files
added_tokens.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "재믺나요": 50140,
3
+ "참지않긬": 50141,
4
+ "이라는둥": 50136,
5
+ "껓뱀": 50135,
6
+ "꽆고": 50139,
7
+ "뮫으면": 50138,
8
+ "띙구렇게": 50137
9
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "unk_token": "[UNK]",
3
+ "sep_token": "[SEP]",
4
+ "pad_token": "[PAD]",
5
+ "cls_token": "[CLS]",
6
+ "mask_token": "[MASK]"
7
+ }
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
+ "do_lower_case": false,
3
+ "unk_token": "[UNK]",
4
+ "sep_token": "[SEP]",
5
+ "pad_token": "[PAD]",
6
+ "cls_token": "[CLS]",
7
+ "mask_token": "[MASK]",
8
+ "tokenize_chinese_chars": true,
9
+ "strip_accents": null,
10
+ "do_basic_tokenize": true,
11
+ "never_split": null,
12
+ "model_max_length": 512
13
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff