Hugging Face's logo

hoang14
/
test_qa

Question Answering
Transformers
PyTorch
distilbert
Model card Files
xet
 Community
1
hoang14 commited on
Commit
54dbe4d
路
1 Parent(s): b07d96f

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +5 -49
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +8 -61
  4. vocab.txt +0 -0
special_tokens_map.json CHANGED
@@ -1,51 +1,7 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "<s>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "mask_token": {
24
- "content": "<mask>",
25
- "lstrip": true,
26
- "normalized": true,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "pad_token": {
31
- "content": "<pad>",
32
- "lstrip": false,
33
- "normalized": true,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
- "sep_token": {
38
- "content": "</s>",
39
- "lstrip": false,
40
- "normalized": true,
41
- "rstrip": false,
42
- "single_word": false
43
- },
44
- "unk_token": {
45
- "content": "<unk>",
46
- "lstrip": false,
47
- "normalized": true,
48
- "rstrip": false,
49
- "single_word": false
50
- }
51
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,66 +1,13 @@
1
  {
2
- "add_prefix_space": false,
3
- "bos_token": {
4
- "__type": "AddedToken",
5
- "content": "<s>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false
10
- },
11
  "clean_up_tokenization_spaces": true,
12
- "cls_token": {
13
- "__type": "AddedToken",
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": true,
17
- "rstrip": false,
18
- "single_word": false
19
- },
20
  "do_lower_case": false,
21
- "eos_token": {
22
- "__type": "AddedToken",
23
- "content": "</s>",
24
- "lstrip": false,
25
- "normalized": true,
26
- "rstrip": false,
27
- "single_word": false
28
- },
29
- "errors": "replace",
30
- "full_tokenizer_file": null,
31
- "mask_token": {
32
- "__type": "AddedToken",
33
- "content": "<mask>",
34
- "lstrip": true,
35
- "normalized": true,
36
- "rstrip": false,
37
- "single_word": false
38
- },
39
  "model_max_length": 512,
40
- "pad_token": {
41
- "__type": "AddedToken",
42
- "content": "<pad>",
43
- "lstrip": false,
44
- "normalized": true,
45
- "rstrip": false,
46
- "single_word": false
47
- },
48
- "sep_token": {
49
- "__type": "AddedToken",
50
- "content": "</s>",
51
- "lstrip": false,
52
- "normalized": true,
53
- "rstrip": false,
54
- "single_word": false
55
- },
56
- "tokenizer_class": "RobertaTokenizer",
57
- "trim_offsets": true,
58
- "unk_token": {
59
- "__type": "AddedToken",
60
- "content": "<unk>",
61
- "lstrip": false,
62
- "normalized": true,
63
- "rstrip": false,
64
- "single_word": false
65
- }
66
  }
 
1
  {
 
 
 
 
 
 
 
 
 
2
  "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
 
 
 
 
 
 
 
4
  "do_lower_case": false,
5
+ "mask_token": "[MASK]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "DistilBertTokenizer",
12
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff