Hugging Face's logo

koreankiwi99
/
colbert_6000

Transformers
Safetensors
bert
Model card Files
xet
 Community
KyuheeKim commited on
Commit
18b9272
·
verified ·
1 Parent(s): 1f22602

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -0
  2. special_tokens_map.json +41 -0
  3. tokenizer_config.json +77 -0
  4. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "[D]": 30523,
3
+ "[Q]": 30522
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[Q]",
4
+ "[D]"
5
+ ],
6
+ "cls_token": {
7
+ "content": "[CLS]",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "mask_token": {
14
+ "content": "[MASK]",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "[PAD]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "sep_token": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "unk_token": {
35
+ "content": "[UNK]",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ }
41
+ }
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
+ "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": "[Q]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "30523": {
52
+ "content": "[D]",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [
61
+ "[Q]",
62
+ "[D]"
63
+ ],
64
+ "clean_up_tokenization_spaces": true,
65
+ "cls_token": "[CLS]",
66
+ "do_basic_tokenize": true,
67
+ "do_lower_case": true,
68
+ "mask_token": "[MASK]",
69
+ "model_max_length": 512,
70
+ "never_split": null,
71
+ "pad_token": "[PAD]",
72
+ "sep_token": "[SEP]",
73
+ "strip_accents": null,
74
+ "tokenize_chinese_chars": true,
75
+ "tokenizer_class": "BertTokenizer",
76
+ "unk_token": "[UNK]"
77
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff