Hugging Face's logo

karina-zadorozhny
/
amino_acid_tokenizer

Model card Files Community
karina-zadorozhny commited on
Commit
69d5eec
·
verified ·
1 Parent(s): 4fac049

Upload 3 files

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +7 -0
  2. tokenizer.json +176 -0
  3. tokenizer_config.json +55 -0
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "<cls>",
3
+ "eos_token": "<eos>",
4
+ "mask_token": "<mask>",
5
+ "pad_token": "<pad>",
6
+ "unk_token": "<unk>"
7
+ }
tokenizer.json ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 32,
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": null,
54
+ "post_processor": {
55
+ "type": "TemplateProcessing",
56
+ "single": [
57
+ {
58
+ "SpecialToken": {
59
+ "id": "<cls>",
60
+ "type_id": 0
61
+ }
62
+ },
63
+ {
64
+ "Sequence": {
65
+ "id": "A",
66
+ "type_id": 0
67
+ }
68
+ },
69
+ {
70
+ "SpecialToken": {
71
+ "id": "<eos>",
72
+ "type_id": 0
73
+ }
74
+ }
75
+ ],
76
+ "pair": [
77
+ {
78
+ "SpecialToken": {
79
+ "id": "<cls>",
80
+ "type_id": 0
81
+ }
82
+ },
83
+ {
84
+ "Sequence": {
85
+ "id": "A",
86
+ "type_id": 0
87
+ }
88
+ },
89
+ {
90
+ "SpecialToken": {
91
+ "id": "<eos>",
92
+ "type_id": 0
93
+ }
94
+ },
95
+ {
96
+ "Sequence": {
97
+ "id": "B",
98
+ "type_id": 1
99
+ }
100
+ },
101
+ {
102
+ "SpecialToken": {
103
+ "id": "<eos>",
104
+ "type_id": 1
105
+ }
106
+ }
107
+ ],
108
+ "special_tokens": {
109
+ "<cls>": {
110
+ "id": "<cls>",
111
+ "ids": [
112
+ 0
113
+ ],
114
+ "tokens": [
115
+ "<cls>"
116
+ ]
117
+ },
118
+ "<eos>": {
119
+ "id": "<eos>",
120
+ "ids": [
121
+ 2
122
+ ],
123
+ "tokens": [
124
+ "<eos>"
125
+ ]
126
+ }
127
+ }
128
+ },
129
+ "decoder": null,
130
+ "model": {
131
+ "type": "BPE",
132
+ "dropout": null,
133
+ "unk_token": "<unk>",
134
+ "continuing_subword_prefix": null,
135
+ "end_of_word_suffix": null,
136
+ "fuse_unk": false,
137
+ "byte_fallback": false,
138
+ "ignore_merges": true,
139
+ "vocab": {
140
+ "<cls>": 0,
141
+ "<pad>": 1,
142
+ "<eos>": 2,
143
+ "<unk>": 3,
144
+ "L": 4,
145
+ "A": 5,
146
+ "G": 6,
147
+ "V": 7,
148
+ "S": 8,
149
+ "E": 9,
150
+ "R": 10,
151
+ "T": 11,
152
+ "I": 12,
153
+ "D": 13,
154
+ "P": 14,
155
+ "K": 15,
156
+ "Q": 16,
157
+ "N": 17,
158
+ "F": 18,
159
+ "Y": 19,
160
+ "M": 20,
161
+ "H": 21,
162
+ "W": 22,
163
+ "C": 23,
164
+ "X": 24,
165
+ "B": 25,
166
+ "U": 26,
167
+ "Z": 27,
168
+ "O": 28,
169
+ ".": 29,
170
+ "-": 30,
171
+ "<null_1>": 31,
172
+ "<mask>": 32
173
+ },
174
+ "merges": []
175
+ }
176
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32": {
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
+ "eos_token": "<eos>",
47
+ "extra_special_tokens": {},
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "padding_side": "right",
52
+ "tokenizer_class": "PreTrainedTokenizerFast",
53
+ "truncation_side": "left",
54
+ "unk_token": "<unk>"
55
+ }