Hugging Face's logo

hazemessam
/
esm3_ddg_v2

Feature Extraction
Transformers
Safetensors
custom_code
Model card Files Community
hazemessam commited on
Commit
493401d
•
1 Parent(s): e821e69

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +10 -0
  2. tokenizer.json +167 -0
  3. tokenizer_config.json +64 -0
special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "|"
4
+ ],
5
+ "cls_token": "<cls>",
6
+ "eos_token": "<eos>",
7
+ "mask_token": "<mask>",
8
+ "pad_token": "<pad>",
9
+ "unk_token": "<unk>"
10
+ }
tokenizer.json ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<cls>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<pad>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "<eos>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<unk>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 31,
44
+ "content": "|",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 32,
53
+ "content": "<mask>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ }
60
+ ],
61
+ "normalizer": null,
62
+ "pre_tokenizer": null,
63
+ "post_processor": {
64
+ "type": "TemplateProcessing",
65
+ "single": [
66
+ {
67
+ "SpecialToken": {
68
+ "id": "<cls>",
69
+ "type_id": 0
70
+ }
71
+ },
72
+ {
73
+ "Sequence": {
74
+ "id": "A",
75
+ "type_id": 0
76
+ }
77
+ },
78
+ {
79
+ "SpecialToken": {
80
+ "id": "<eos>",
81
+ "type_id": 0
82
+ }
83
+ }
84
+ ],
85
+ "pair": [
86
+ {
87
+ "Sequence": {
88
+ "id": "A",
89
+ "type_id": 0
90
+ }
91
+ },
92
+ {
93
+ "Sequence": {
94
+ "id": "B",
95
+ "type_id": 1
96
+ }
97
+ }
98
+ ],
99
+ "special_tokens": {
100
+ "<cls>": {
101
+ "id": "<cls>",
102
+ "ids": [
103
+ 0
104
+ ],
105
+ "tokens": [
106
+ "<cls>"
107
+ ]
108
+ },
109
+ "<eos>": {
110
+ "id": "<eos>",
111
+ "ids": [
112
+ 2
113
+ ],
114
+ "tokens": [
115
+ "<eos>"
116
+ ]
117
+ }
118
+ }
119
+ },
120
+ "decoder": null,
121
+ "model": {
122
+ "type": "BPE",
123
+ "dropout": null,
124
+ "unk_token": "<unk>",
125
+ "continuing_subword_prefix": null,
126
+ "end_of_word_suffix": null,
127
+ "fuse_unk": false,
128
+ "byte_fallback": false,
129
+ "ignore_merges": false,
130
+ "vocab": {
131
+ "<cls>": 0,
132
+ "<pad>": 1,
133
+ "<eos>": 2,
134
+ "<unk>": 3,
135
+ "L": 4,
136
+ "A": 5,
137
+ "G": 6,
138
+ "V": 7,
139
+ "S": 8,
140
+ "E": 9,
141
+ "R": 10,
142
+ "T": 11,
143
+ "I": 12,
144
+ "D": 13,
145
+ "P": 14,
146
+ "K": 15,
147
+ "Q": 16,
148
+ "N": 17,
149
+ "F": 18,
150
+ "Y": 19,
151
+ "M": 20,
152
+ "H": 21,
153
+ "W": 22,
154
+ "C": 23,
155
+ "X": 24,
156
+ "B": 25,
157
+ "U": 26,
158
+ "Z": 27,
159
+ "O": 28,
160
+ ".": 29,
161
+ "-": 30,
162
+ "|": 31,
163
+ "<mask>": 32
164
+ },
165
+ "merges": []
166
+ }
167
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<cls>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<eos>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "31": {
36
+ "content": "|",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32": {
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
+ "|"
54
+ ],
55
+ "bos_token": "<cls>",
56
+ "clean_up_tokenization_spaces": false,
57
+ "cls_token": "<cls>",
58
+ "eos_token": "<eos>",
59
+ "mask_token": "<mask>",
60
+ "model_max_length": 1000000000000000019884624838656,
61
+ "pad_token": "<pad>",
62
+ "tokenizer_class": "EsmSequenceTokenizer",
63
+ "unk_token": "<unk>"
64
+ }