Hugging Face's logo

adrianhenkel
/
lucid-prot-tokenizer

Model card Files Community
adrianhenkel commited on
Commit
2e9d126
•
1 Parent(s): 30551b1

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +22 -0
  2. special_tokens_map.json +7 -0
  3. tokenizer.json +360 -0
  4. tokenizer_config.json +16 -0
  5. vocab.txt +30 -0
added_tokens.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "a": 30,
3
+ "c": 31,
4
+ "d": 32,
5
+ "e": 33,
6
+ "f": 34,
7
+ "g": 35,
8
+ "h": 36,
9
+ "i": 37,
10
+ "k": 38,
11
+ "l": 39,
12
+ "m": 40,
13
+ "n": 41,
14
+ "p": 42,
15
+ "q": 43,
16
+ "r": 44,
17
+ "s": 45,
18
+ "t": 46,
19
+ "v": 47,
20
+ "w": 48,
21
+ "y": 49
22
+ }
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 +1,360 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[UNK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[CLS]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[SEP]",
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
+ "id": 30,
53
+ "content": "a",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": true,
58
+ "special": false
59
+ },
60
+ {
61
+ "id": 31,
62
+ "content": "c",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": true,
67
+ "special": false
68
+ },
69
+ {
70
+ "id": 32,
71
+ "content": "d",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": true,
76
+ "special": false
77
+ },
78
+ {
79
+ "id": 33,
80
+ "content": "e",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": true,
85
+ "special": false
86
+ },
87
+ {
88
+ "id": 34,
89
+ "content": "f",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": true,
94
+ "special": false
95
+ },
96
+ {
97
+ "id": 35,
98
+ "content": "g",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": true,
103
+ "special": false
104
+ },
105
+ {
106
+ "id": 36,
107
+ "content": "h",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": true,
112
+ "special": false
113
+ },
114
+ {
115
+ "id": 37,
116
+ "content": "i",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": true,
121
+ "special": false
122
+ },
123
+ {
124
+ "id": 38,
125
+ "content": "k",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": true,
130
+ "special": false
131
+ },
132
+ {
133
+ "id": 39,
134
+ "content": "l",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": true,
139
+ "special": false
140
+ },
141
+ {
142
+ "id": 40,
143
+ "content": "m",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": true,
148
+ "special": false
149
+ },
150
+ {
151
+ "id": 41,
152
+ "content": "n",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": true,
157
+ "special": false
158
+ },
159
+ {
160
+ "id": 42,
161
+ "content": "p",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": true,
166
+ "special": false
167
+ },
168
+ {
169
+ "id": 43,
170
+ "content": "q",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": true,
175
+ "special": false
176
+ },
177
+ {
178
+ "id": 44,
179
+ "content": "r",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": true,
184
+ "special": false
185
+ },
186
+ {
187
+ "id": 45,
188
+ "content": "s",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": true,
193
+ "special": false
194
+ },
195
+ {
196
+ "id": 46,
197
+ "content": "t",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": true,
202
+ "special": false
203
+ },
204
+ {
205
+ "id": 47,
206
+ "content": "v",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": true,
211
+ "special": false
212
+ },
213
+ {
214
+ "id": 48,
215
+ "content": "w",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": true,
220
+ "special": false
221
+ },
222
+ {
223
+ "id": 49,
224
+ "content": "y",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": true,
229
+ "special": false
230
+ }
231
+ ],
232
+ "normalizer": {
233
+ "type": "BertNormalizer",
234
+ "clean_text": true,
235
+ "handle_chinese_chars": true,
236
+ "strip_accents": null,
237
+ "lowercase": false
238
+ },
239
+ "pre_tokenizer": {
240
+ "type": "BertPreTokenizer"
241
+ },
242
+ "post_processor": {
243
+ "type": "TemplateProcessing",
244
+ "single": [
245
+ {
246
+ "SpecialToken": {
247
+ "id": "[CLS]",
248
+ "type_id": 0
249
+ }
250
+ },
251
+ {
252
+ "Sequence": {
253
+ "id": "A",
254
+ "type_id": 0
255
+ }
256
+ },
257
+ {
258
+ "SpecialToken": {
259
+ "id": "[SEP]",
260
+ "type_id": 0
261
+ }
262
+ }
263
+ ],
264
+ "pair": [
265
+ {
266
+ "SpecialToken": {
267
+ "id": "[CLS]",
268
+ "type_id": 0
269
+ }
270
+ },
271
+ {
272
+ "Sequence": {
273
+ "id": "A",
274
+ "type_id": 0
275
+ }
276
+ },
277
+ {
278
+ "SpecialToken": {
279
+ "id": "[SEP]",
280
+ "type_id": 0
281
+ }
282
+ },
283
+ {
284
+ "Sequence": {
285
+ "id": "B",
286
+ "type_id": 1
287
+ }
288
+ },
289
+ {
290
+ "SpecialToken": {
291
+ "id": "[SEP]",
292
+ "type_id": 1
293
+ }
294
+ }
295
+ ],
296
+ "special_tokens": {
297
+ "[CLS]": {
298
+ "id": "[CLS]",
299
+ "ids": [
300
+ 2
301
+ ],
302
+ "tokens": [
303
+ "[CLS]"
304
+ ]
305
+ },
306
+ "[SEP]": {
307
+ "id": "[SEP]",
308
+ "ids": [
309
+ 3
310
+ ],
311
+ "tokens": [
312
+ "[SEP]"
313
+ ]
314
+ }
315
+ }
316
+ },
317
+ "decoder": {
318
+ "type": "WordPiece",
319
+ "prefix": "##",
320
+ "cleanup": true
321
+ },
322
+ "model": {
323
+ "type": "WordPiece",
324
+ "unk_token": "[UNK]",
325
+ "continuing_subword_prefix": "##",
326
+ "max_input_chars_per_word": 100,
327
+ "vocab": {
328
+ "[PAD]": 0,
329
+ "[UNK]": 1,
330
+ "[CLS]": 2,
331
+ "[SEP]": 3,
332
+ "[MASK]": 4,
333
+ "L": 5,
334
+ "A": 6,
335
+ "G": 7,
336
+ "V": 8,
337
+ "E": 9,
338
+ "S": 10,
339
+ "I": 11,
340
+ "K": 12,
341
+ "R": 13,
342
+ "D": 14,
343
+ "T": 15,
344
+ "P": 16,
345
+ "N": 17,
346
+ "Q": 18,
347
+ "F": 19,
348
+ "Y": 20,
349
+ "M": 21,
350
+ "H": 22,
351
+ "C": 23,
352
+ "W": 24,
353
+ "X": 25,
354
+ "U": 26,
355
+ "B": 27,
356
+ "Z": 28,
357
+ "O": 29
358
+ }
359
+ }
360
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "full_tokenizer_file": null,
6
+ "mask_token": "[MASK]",
7
+ "name_or_path": "Rostlab/prot_bert",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
vocab.txt ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [PAD]
2
+ [UNK]
3
+ [CLS]
4
+ [SEP]
5
+ [MASK]
6
+ L
7
+ A
8
+ G
9
+ V
10
+ E
11
+ S
12
+ I
13
+ K
14
+ R
15
+ D
16
+ T
17
+ P
18
+ N
19
+ Q
20
+ F
21
+ Y
22
+ M
23
+ H
24
+ C
25
+ W
26
+ X
27
+ U
28
+ B
29
+ Z
30
+ O