LeoCordoba commited on
Commit
ebb269e
1 Parent(s): b52cb14

commit files to HF hub

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +13 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +25 -0
special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+
3
+ "unk_token": "[UNK]",
4
+
5
+ "sep_token": "[SEP]",
6
+
7
+ "pad_token": "[PAD]",
8
+
9
+ "cls_token": "[CLS]",
10
+
11
+ "mask_token": "[MASK]"
12
+
13
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+
3
+ "do_lower_case": true,
4
+
5
+ "unk_token": "[UNK]",
6
+
7
+ "sep_token": "[SEP]",
8
+
9
+ "pad_token": "[PAD]",
10
+
11
+ "cls_token": "[CLS]",
12
+
13
+ "mask_token": "[MASK]",
14
+
15
+ "tokenize_chinese_chars": true,
16
+
17
+ "strip_accents": false,
18
+
19
+ "do_basic_tokenize": true,
20
+
21
+ "never_split": null,
22
+
23
+ "model_max_length": 512
24
+
25
+ }