CurtisJeon commited on
Commit
0144718
1 Parent(s): 1cdbdc8

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +9 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +18 -0
  4. vocab.txt +0 -0
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
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 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "eos_token": "[SEP]",
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "name_or_path": "klue/roberta-large",
10
+ "never_split": null,
11
+ "pad_token": "[PAD]",
12
+ "sep_token": "[SEP]",
13
+ "special_tokens_map_file": "/data/ephemeral/huggingface/models--klue--roberta-large/snapshots/28d911204e9022eda172571ca8cc61eaffd942f7/special_tokens_map.json",
14
+ "strip_accents": null,
15
+ "tokenize_chinese_chars": true,
16
+ "tokenizer_class": "BertTokenizer",
17
+ "unk_token": "[UNK]"
18
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff