t-tsuma commited on
Commit
b24ad91
1 Parent(s): 1446771

Added a tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +10 -0
  2. tokenizer_config.json +77 -0
  3. vocab.txt +0 -0
special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[EMPTY]"
4
+ ],
5
+ "cls_token": "[CLS]",
6
+ "mask_token": "[MASK]",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "unk_token": "[UNK]"
10
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[EMPTY]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "100": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "101": {
28
+ "content": "[CLS]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "102": {
36
+ "content": "[SEP]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "103": {
44
+ "content": "[MASK]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "additional_special_tokens": [
53
+ "[EMPTY]"
54
+ ],
55
+ "cell_trim_length": -1,
56
+ "clean_up_tokenization_spaces": true,
57
+ "cls_token": "[CLS]",
58
+ "do_basic_tokenize": true,
59
+ "do_lower_case": true,
60
+ "drop_rows_to_fit": false,
61
+ "empty_token": "[EMPTY]",
62
+ "mask_token": "[MASK]",
63
+ "max_column_id": 512,
64
+ "max_question_length": null,
65
+ "max_row_id": 512,
66
+ "min_question_length": null,
67
+ "model_max_length": 512,
68
+ "never_split": null,
69
+ "pad_token": "[PAD]",
70
+ "sep_token": "[SEP]",
71
+ "strip_accents": null,
72
+ "strip_column_names": false,
73
+ "tokenize_chinese_chars": true,
74
+ "tokenizer_class": "TapasTokenizer",
75
+ "unk_token": "[UNK]",
76
+ "update_answer_coordinates": false
77
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff