Hugging Face's logo

AI4Protein
/
deep_bpe_50

Feature Extraction
Transformers
PyTorch
roformer
fill-mask
Model card Files
xet
Community
3
GinnM commited on
Commit
d964738
·
1 Parent(s): b8c54d9

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +9 -0
  2. tokenizer.json +216 -0
  3. tokenizer_config.json +5 -0
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<cls>",
3
+ "cls_token": "<cls>",
4
+ "eos_token": "<sep>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "<sep>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer.json ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<pad>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<cls>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "<sep>",
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": 4,
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": "<sep>",
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": "<sep>",
92
+ "type_id": 0
93
+ }
94
+ },
95
+ {
96
+ "Sequence": {
97
+ "id": "B",
98
+ "type_id": 1
99
+ }
100
+ },
101
+ {
102
+ "SpecialToken": {
103
+ "id": "<sep>",
104
+ "type_id": 1
105
+ }
106
+ }
107
+ ],
108
+ "special_tokens": {
109
+ "<cls>": {
110
+ "id": "<cls>",
111
+ "ids": [
112
+ 1
113
+ ],
114
+ "tokens": [
115
+ "<cls>"
116
+ ]
117
+ },
118
+ "<sep>": {
119
+ "id": "<sep>",
120
+ "ids": [
121
+ 2
122
+ ],
123
+ "tokens": [
124
+ "<sep>"
125
+ ]
126
+ }
127
+ }
128
+ },
129
+ "decoder": {
130
+ "type": "BPEDecoder",
131
+ "suffix": "</w>"
132
+ },
133
+ "model": {
134
+ "type": "BPE",
135
+ "dropout": null,
136
+ "unk_token": null,
137
+ "continuing_subword_prefix": null,
138
+ "end_of_word_suffix": null,
139
+ "fuse_unk": false,
140
+ "byte_fallback": false,
141
+ "vocab": {
142
+ "<pad>": 0,
143
+ "<cls>": 1,
144
+ "<sep>": 2,
145
+ "<unk>": 3,
146
+ "<mask>": 4,
147
+ "A": 5,
148
+ "B": 6,
149
+ "C": 7,
150
+ "D": 8,
151
+ "E": 9,
152
+ "F": 10,
153
+ "G": 11,
154
+ "H": 12,
155
+ "I": 13,
156
+ "K": 14,
157
+ "L": 15,
158
+ "M": 16,
159
+ "N": 17,
160
+ "O": 18,
161
+ "P": 19,
162
+ "Q": 20,
163
+ "R": 21,
164
+ "S": 22,
165
+ "T": 23,
166
+ "U": 24,
167
+ "V": 25,
168
+ "W": 26,
169
+ "X": 27,
170
+ "Y": 28,
171
+ "Z": 29,
172
+ "AA": 30,
173
+ "LL": 31,
174
+ "SS": 32,
175
+ "LA": 33,
176
+ "LS": 34,
177
+ "GG": 35,
178
+ "LV": 36,
179
+ "LR": 37,
180
+ "LE": 38,
181
+ "LG": 39,
182
+ "LT": 40,
183
+ "AV": 41,
184
+ "AG": 42,
185
+ "LP": 43,
186
+ "LD": 44,
187
+ "LI": 45,
188
+ "AS": 46,
189
+ "EE": 47,
190
+ "RR": 48,
191
+ "LK": 49
192
+ },
193
+ "merges": [
194
+ "A A",
195
+ "L L",
196
+ "S S",
197
+ "L A",
198
+ "L S",
199
+ "G G",
200
+ "L V",
201
+ "L R",
202
+ "L E",
203
+ "L G",
204
+ "L T",
205
+ "A V",
206
+ "A G",
207
+ "L P",
208
+ "L D",
209
+ "L I",
210
+ "A S",
211
+ "E E",
212
+ "R R",
213
+ "L K"
214
+ ]
215
+ }
216
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "model_max_length": 1000000000000000019884624838656,
4
+ "tokenizer_class": "PreTrainedTokenizerFast"
5
+ }