Hugging Face's logo

MichelNivard
/
GPCRBert-v0.1

Fill-Mask
Transformers
Safetensors
modernbert
biology
Proteins
Model card Files
xet
Community
MichelNivard commited on
Commit
280b43c
·
verified ·
1 Parent(s): 90ab2c1

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +7 -0
  2. tokenizer.json +98 -0
  3. tokenizer_config.json +53 -0
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 24,
8
+ "content": "[UNK]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 25,
17
+ "content": "[PAD]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 26,
26
+ "content": "[CLS]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 27,
35
+ "content": "[SEP]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 28,
44
+ "content": "[MASK]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ }
51
+ ],
52
+ "normalizer": null,
53
+ "pre_tokenizer": {
54
+ "type": "Split",
55
+ "pattern": {
56
+ "String": ""
57
+ },
58
+ "behavior": "Isolated",
59
+ "invert": false
60
+ },
61
+ "post_processor": null,
62
+ "decoder": null,
63
+ "model": {
64
+ "type": "WordLevel",
65
+ "vocab": {
66
+ "A": 0,
67
+ "R": 1,
68
+ "N": 2,
69
+ "D": 3,
70
+ "C": 4,
71
+ "Q": 5,
72
+ "E": 6,
73
+ "G": 7,
74
+ "H": 8,
75
+ "I": 9,
76
+ "L": 10,
77
+ "K": 11,
78
+ "M": 12,
79
+ "F": 13,
80
+ "P": 14,
81
+ "S": 15,
82
+ "T": 16,
83
+ "W": 17,
84
+ "Y": 18,
85
+ "V": 19,
86
+ "B": 20,
87
+ "Z": 21,
88
+ "X": 22,
89
+ "-": 23,
90
+ "[UNK]": 24,
91
+ "[PAD]": 25,
92
+ "[CLS]": 26,
93
+ "[SEP]": 27,
94
+ "[MASK]": 28
95
+ },
96
+ "unk_token": "[UNK]"
97
+ }
98
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "24": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "25": {
12
+ "content": "[PAD]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "26": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "27": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "28": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "extra_special_tokens": {},
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "tokenizer_class": "PreTrainedTokenizer",
52
+ "unk_token": "[UNK]"
53
+ }