JuanJoseMV commited on
Commit
843f796
1 Parent(s): 0bc5f78

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[NEGATIVE-0]": 30522,
3
+ "[NEGATIVE-1]": 30523,
4
+ "[NEGATIVE-2]": 30524,
5
+ "[POSITIVE-0]": 30525,
6
+ "[POSITIVE-1]": 30526,
7
+ "[POSITIVE-2]": 30527
8
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[NEGATIVE-0]",
4
+ "[NEGATIVE-1]",
5
+ "[NEGATIVE-2]",
6
+ "[POSITIVE-0]",
7
+ "[POSITIVE-1]",
8
+ "[POSITIVE-2]"
9
+ ],
10
+ "cls_token": "[CLS]",
11
+ "mask_token": "[MASK]",
12
+ "pad_token": "[PAD]",
13
+ "sep_token": "[SEP]",
14
+ "unk_token": "[UNK]"
15
+ }
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
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff