Hugging Face's logo

kimsan0622
/
bigbird-base

Fill-Mask
Transformers
PyTorch
big_bird
Inference Endpoints
Model card Files Community
kimsan0622 commited on
Commit
6b7e614
•
1 Parent(s): 85eff89

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +51 -0
  2. spiece.model +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +62 -0
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[CLS]",
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": "[SEP]",
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
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4368e6b7901e8c54bd62326ca5a5063eba36c31d74995a599a5be77a0cd5cfd0
3
+ size 1592581
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "cls_token": {
11
+ "__type": "AddedToken",
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "__type": "AddedToken",
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "mask_token": {
27
+ "__type": "AddedToken",
28
+ "content": "[MASK]",
29
+ "lstrip": true,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "model_max_length": 4096,
35
+ "pad_token": {
36
+ "__type": "AddedToken",
37
+ "content": "<pad>",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false
42
+ },
43
+ "sep_token": {
44
+ "__type": "AddedToken",
45
+ "content": "[SEP]",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ },
51
+ "sp_model_kwargs": {},
52
+ "special_tokens_map_file": "vocab/ko_en/spiece/ko20000vs64000_ext/special_tokens_map.json",
53
+ "tokenizer_class": "BigBirdTokenizer",
54
+ "unk_token": {
55
+ "__type": "AddedToken",
56
+ "content": "<unk>",
57
+ "lstrip": false,
58
+ "normalized": true,
59
+ "rstrip": false,
60
+ "single_word": false
61
+ }
62
+ }