bneb-consensus commited on
Commit
0647197
·
verified ·
1 Parent(s): 0c60e14

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[CLS]": 101,
3
+ "[MASK]": 103,
4
+ "[PAD]": 0,
5
+ "[SEP]": 102,
6
+ "[UNK]": 100,
7
+ "rrl": 30522
8
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[PAD]",
4
+ "[UNK]",
5
+ "[CLS]",
6
+ "[SEP]",
7
+ "[MASK]"
8
+ ],
9
+ "cls_token": "[CLS]",
10
+ "mask_token": "[MASK]",
11
+ "pad_token": "[PAD]",
12
+ "sep_token": "[SEP]",
13
+ "unk_token": "[UNK]"
14
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30522": {
44
+ "content": "rrl",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ }
51
+ },
52
+ "additional_special_tokens": [
53
+ "[PAD]",
54
+ "[UNK]",
55
+ "[CLS]",
56
+ "[SEP]",
57
+ "[MASK]"
58
+ ],
59
+ "clean_up_tokenization_spaces": true,
60
+ "cls_token": "[CLS]",
61
+ "do_lower_case": true,
62
+ "mask_token": "[MASK]",
63
+ "model_max_length": 512,
64
+ "pad_token": "[PAD]",
65
+ "sep_token": "[SEP]",
66
+ "strip_accents": null,
67
+ "tokenize_chinese_chars": true,
68
+ "tokenizer_class": "DistilBertTokenizer",
69
+ "unk_token": "[UNK]"
70
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff