Parsa commited on
Commit
6730ebc
1 Parent(s): 593e4da

add tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 592,
3
+ "<s>": 591
4
+ }
merges.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ #version: 0.2 - Trained by `huggingface/tokenizers`
special_tokens_map.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": "[CLS]",
10
+ "eos_token": {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "mask_token": {
18
+ "content": "[MASK]",
19
+ "lstrip": true,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "[PAD]",
25
+ "sep_token": "[SEP]",
26
+ "unk_token": "[UNK]"
27
+ }
tokenizer.json ADDED
@@ -0,0 +1,698 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 11,
17
+ "content": "[UNK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 12,
26
+ "content": "[CLS]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 13,
35
+ "content": "[SEP]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 14,
44
+ "content": "[MASK]",
45
+ "single_word": false,
46
+ "lstrip": true,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 591,
53
+ "content": "<s>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": true,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 592,
62
+ "content": "</s>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": true,
67
+ "special": true
68
+ }
69
+ ],
70
+ "normalizer": null,
71
+ "pre_tokenizer": {
72
+ "type": "ByteLevel",
73
+ "add_prefix_space": false,
74
+ "trim_offsets": true,
75
+ "use_regex": true
76
+ },
77
+ "post_processor": {
78
+ "type": "RobertaProcessing",
79
+ "sep": [
80
+ "[SEP]",
81
+ 13
82
+ ],
83
+ "cls": [
84
+ "[CLS]",
85
+ 12
86
+ ],
87
+ "trim_offsets": true,
88
+ "add_prefix_space": false
89
+ },
90
+ "decoder": {
91
+ "type": "ByteLevel",
92
+ "add_prefix_space": true,
93
+ "trim_offsets": true,
94
+ "use_regex": true
95
+ },
96
+ "model": {
97
+ "type": "BPE",
98
+ "dropout": null,
99
+ "unk_token": null,
100
+ "continuing_subword_prefix": "",
101
+ "end_of_word_suffix": "",
102
+ "fuse_unk": false,
103
+ "vocab": {
104
+ "[PAD]": 0,
105
+ "[unused1]": 1,
106
+ "[unused2]": 2,
107
+ "[unused3]": 3,
108
+ "[unused4]": 4,
109
+ "[unused5]": 5,
110
+ "[unused6]": 6,
111
+ "[unused7]": 7,
112
+ "[unused8]": 8,
113
+ "[unused9]": 9,
114
+ "[unused10]": 10,
115
+ "[UNK]": 11,
116
+ "[CLS]": 12,
117
+ "[SEP]": 13,
118
+ "[MASK]": 14,
119
+ "c": 15,
120
+ "C": 16,
121
+ "(": 17,
122
+ ")": 18,
123
+ "O": 19,
124
+ "1": 20,
125
+ "2": 21,
126
+ "=": 22,
127
+ "N": 23,
128
+ ".": 24,
129
+ "n": 25,
130
+ "3": 26,
131
+ "F": 27,
132
+ "Cl": 28,
133
+ ">>": 29,
134
+ "~": 30,
135
+ "-": 31,
136
+ "4": 32,
137
+ "[C@H]": 33,
138
+ "S": 34,
139
+ "[C@@H]": 35,
140
+ "[O-]": 36,
141
+ "Br": 37,
142
+ "#": 38,
143
+ "/": 39,
144
+ "[nH]": 40,
145
+ "[N+]": 41,
146
+ "s": 42,
147
+ "5": 43,
148
+ "o": 44,
149
+ "P": 45,
150
+ "[Na+]": 46,
151
+ "[Si]": 47,
152
+ "I": 48,
153
+ "[Na]": 49,
154
+ "[Pd]": 50,
155
+ "[K+]": 51,
156
+ "[K]": 52,
157
+ "[P]": 53,
158
+ "B": 54,
159
+ "[C@]": 55,
160
+ "[C@@]": 56,
161
+ "[Cl-]": 57,
162
+ "6": 58,
163
+ "[OH-]": 59,
164
+ "\\": 60,
165
+ "[N-]": 61,
166
+ "[Li]": 62,
167
+ "[H]": 63,
168
+ "[2H]": 64,
169
+ "[NH4+]": 65,
170
+ "[c-]": 66,
171
+ "[P-]": 67,
172
+ "[Cs+]": 68,
173
+ "[Li+]": 69,
174
+ "[Cs]": 70,
175
+ "[NaH]": 71,
176
+ "[H-]": 72,
177
+ "[O+]": 73,
178
+ "[BH4-]": 74,
179
+ "[Cu]": 75,
180
+ "7": 76,
181
+ "[Mg]": 77,
182
+ "[Fe+2]": 78,
183
+ "[n+]": 79,
184
+ "[Sn]": 80,
185
+ "[BH-]": 81,
186
+ "[Pd+2]": 82,
187
+ "[CH]": 83,
188
+ "[I-]": 84,
189
+ "[Br-]": 85,
190
+ "[C-]": 86,
191
+ "[Zn]": 87,
192
+ "[B-]": 88,
193
+ "[F-]": 89,
194
+ "[Al]": 90,
195
+ "[P+]": 91,
196
+ "[BH3-]": 92,
197
+ "[Fe]": 93,
198
+ "[C]": 94,
199
+ "[AlH4]": 95,
200
+ "[Ni]": 96,
201
+ "[SiH]": 97,
202
+ "8": 98,
203
+ "[Cu+2]": 99,
204
+ "[Mn]": 100,
205
+ "[AlH]": 101,
206
+ "[nH+]": 102,
207
+ "[AlH4-]": 103,
208
+ "[O-2]": 104,
209
+ "[Cr]": 105,
210
+ "[Mg+2]": 106,
211
+ "[NH3+]": 107,
212
+ "[S@]": 108,
213
+ "[Pt]": 109,
214
+ "[Al+3]": 110,
215
+ "[S@@]": 111,
216
+ "[S-]": 112,
217
+ "[Ti]": 113,
218
+ "[Zn+2]": 114,
219
+ "[PH]": 115,
220
+ "[NH2+]": 116,
221
+ "[Ru]": 117,
222
+ "[Ag+]": 118,
223
+ "[S+]": 119,
224
+ "[I+3]": 120,
225
+ "[NH+]": 121,
226
+ "[Ca+2]": 122,
227
+ "[Ag]": 123,
228
+ "9": 124,
229
+ "[Os]": 125,
230
+ "[Se]": 126,
231
+ "[SiH2]": 127,
232
+ "[Ca]": 128,
233
+ "[Ti+4]": 129,
234
+ "[Ac]": 130,
235
+ "[Cu+]": 131,
236
+ "[S]": 132,
237
+ "[Rh]": 133,
238
+ "[Cl+3]": 134,
239
+ "[cH-]": 135,
240
+ "[Zn+]": 136,
241
+ "[O]": 137,
242
+ "[Cl+]": 138,
243
+ "[SH]": 139,
244
+ "[H+]": 140,
245
+ "[Pd+]": 141,
246
+ "[se]": 142,
247
+ "[PH+]": 143,
248
+ "[I]": 144,
249
+ "[Pt+2]": 145,
250
+ "[C+]": 146,
251
+ "[Mg+]": 147,
252
+ "[Hg]": 148,
253
+ "[W]": 149,
254
+ "[SnH]": 150,
255
+ "[SiH3]": 151,
256
+ "[Fe+3]": 152,
257
+ "[NH]": 153,
258
+ "[Mo]": 154,
259
+ "[CH2+]": 155,
260
+ "%10": 156,
261
+ "[CH2-]": 157,
262
+ "[CH2]": 158,
263
+ "[n-]": 159,
264
+ "[Ce+4]": 160,
265
+ "[NH-]": 161,
266
+ "[Co]": 162,
267
+ "[I+]": 163,
268
+ "[PH2]": 164,
269
+ "[Pt+4]": 165,
270
+ "[Ce]": 166,
271
+ "[B]": 167,
272
+ "[Sn+2]": 168,
273
+ "[Ba+2]": 169,
274
+ "%11": 170,
275
+ "[Fe-3]": 171,
276
+ "[18F]": 172,
277
+ "[SH-]": 173,
278
+ "[Pb+2]": 174,
279
+ "[Os-2]": 175,
280
+ "[Zr+4]": 176,
281
+ "[N]": 177,
282
+ "[Ir]": 178,
283
+ "[Bi]": 179,
284
+ "[Ni+2]": 180,
285
+ "[P@]": 181,
286
+ "[Co+2]": 182,
287
+ "[s+]": 183,
288
+ "[As]": 184,
289
+ "[P+3]": 185,
290
+ "[Hg+2]": 186,
291
+ "[Yb+3]": 187,
292
+ "[CH-]": 188,
293
+ "[Zr+2]": 189,
294
+ "[Mn+2]": 190,
295
+ "[CH+]": 191,
296
+ "[In]": 192,
297
+ "[KH]": 193,
298
+ "[Ce+3]": 194,
299
+ "[Zr]": 195,
300
+ "[AlH2-]": 196,
301
+ "[OH2+]": 197,
302
+ "[Ti+3]": 198,
303
+ "[Rh+2]": 199,
304
+ "[Sb]": 200,
305
+ "[S-2]": 201,
306
+ "%12": 202,
307
+ "[P@@]": 203,
308
+ "[Si@H]": 204,
309
+ "[Mn+4]": 205,
310
+ "p": 206,
311
+ "[Ba]": 207,
312
+ "[NH2-]": 208,
313
+ "[Ge]": 209,
314
+ "[Pb+4]": 210,
315
+ "[Cr+3]": 211,
316
+ "[Au]": 212,
317
+ "[LiH]": 213,
318
+ "[Sc+3]": 214,
319
+ "[o+]": 215,
320
+ "[Rh-3]": 216,
321
+ "%13": 217,
322
+ "[Br]": 218,
323
+ "[Sb-]": 219,
324
+ "[S@+]": 220,
325
+ "[I+2]": 221,
326
+ "[Ar]": 222,
327
+ "[V]": 223,
328
+ "[Cu-]": 224,
329
+ "[Al-]": 225,
330
+ "[Te]": 226,
331
+ "[13c]": 227,
332
+ "[13C]": 228,
333
+ "[Cl]": 229,
334
+ "[PH4+]": 230,
335
+ "[SiH4]": 231,
336
+ "[te]": 232,
337
+ "[CH3-]": 233,
338
+ "[S@@+]": 234,
339
+ "[Rh+3]": 235,
340
+ "[SH+]": 236,
341
+ "[Bi+3]": 237,
342
+ "[Br+2]": 238,
343
+ "[La]": 239,
344
+ "[La+3]": 240,
345
+ "[Pt-2]": 241,
346
+ "[N@@]": 242,
347
+ "[PH3+]": 243,
348
+ "[N@]": 244,
349
+ "[Si+4]": 245,
350
+ "[Sr+2]": 246,
351
+ "[Al+]": 247,
352
+ "[Pb]": 248,
353
+ "[SeH]": 249,
354
+ "[Si-]": 250,
355
+ "[V+5]": 251,
356
+ "[Y+3]": 252,
357
+ "[Re]": 253,
358
+ "[Ru+]": 254,
359
+ "[Sm]": 255,
360
+ "*": 256,
361
+ "[3H]": 257,
362
+ "[NH2]": 258,
363
+ "[Ag-]": 259,
364
+ "[13CH3]": 260,
365
+ "[OH+]": 261,
366
+ "[Ru+3]": 262,
367
+ "[OH]": 263,
368
+ "[Gd+3]": 264,
369
+ "[13CH2]": 265,
370
+ "[In+3]": 266,
371
+ "[Si@@]": 267,
372
+ "[Si@]": 268,
373
+ "[Ti+2]": 269,
374
+ "[Sn+]": 270,
375
+ "[Cl+2]": 271,
376
+ "[AlH-]": 272,
377
+ "[Pd-2]": 273,
378
+ "[SnH3]": 274,
379
+ "[B+3]": 275,
380
+ "[Cu-2]": 276,
381
+ "[Nd+3]": 277,
382
+ "[Pb+3]": 278,
383
+ "[13cH]": 279,
384
+ "[Fe-4]": 280,
385
+ "[Ga]": 281,
386
+ "[Sn+4]": 282,
387
+ "[Hg+]": 283,
388
+ "[11CH3]": 284,
389
+ "[Hf]": 285,
390
+ "[Pr]": 286,
391
+ "[Y]": 287,
392
+ "[S+2]": 288,
393
+ "[Cd]": 289,
394
+ "[Cr+6]": 290,
395
+ "[Zr+3]": 291,
396
+ "[Rh+]": 292,
397
+ "[CH3]": 293,
398
+ "[N-3]": 294,
399
+ "[Hf+2]": 295,
400
+ "[Th]": 296,
401
+ "[Sb+3]": 297,
402
+ "%14": 298,
403
+ "[Cr+2]": 299,
404
+ "[Ru+2]": 300,
405
+ "[Hf+4]": 301,
406
+ "[14C]": 302,
407
+ "[Ta]": 303,
408
+ "[Tl+]": 304,
409
+ "[B+]": 305,
410
+ "[Os+4]": 306,
411
+ "[PdH2]": 307,
412
+ "[Pd-]": 308,
413
+ "[Cd+2]": 309,
414
+ "[Co+3]": 310,
415
+ "[S+4]": 311,
416
+ "[Nb+5]": 312,
417
+ "[123I]": 313,
418
+ "[c+]": 314,
419
+ "[Rb+]": 315,
420
+ "[V+2]": 316,
421
+ "[CH3+]": 317,
422
+ "[Ag+2]": 318,
423
+ "[cH+]": 319,
424
+ "[Mn+3]": 320,
425
+ "[Se-]": 321,
426
+ "[As-]": 322,
427
+ "[Eu+3]": 323,
428
+ "[SH2]": 324,
429
+ "[Sm+3]": 325,
430
+ "[IH+]": 326,
431
+ "%15": 327,
432
+ "[OH3+]": 328,
433
+ "[PH3]": 329,
434
+ "[IH2+]": 330,
435
+ "[SH2+]": 331,
436
+ "[Ir+3]": 332,
437
+ "[AlH3]": 333,
438
+ "[Sc]": 334,
439
+ "[Yb]": 335,
440
+ "[15NH2]": 336,
441
+ "[Lu]": 337,
442
+ "[sH+]": 338,
443
+ "[Gd]": 339,
444
+ "[18F-]": 340,
445
+ "[SH3+]": 341,
446
+ "[SnH4]": 342,
447
+ "[TeH]": 343,
448
+ "[Si@@H]": 344,
449
+ "[Ga+3]": 345,
450
+ "[CaH2]": 346,
451
+ "[Tl]": 347,
452
+ "[Ta+5]": 348,
453
+ "[GeH]": 349,
454
+ "[Br+]": 350,
455
+ "[Sr]": 351,
456
+ "[Tl+3]": 352,
457
+ "[Sm+2]": 353,
458
+ "[PH5]": 354,
459
+ "%16": 355,
460
+ "[N@@+]": 356,
461
+ "[Au+3]": 357,
462
+ "[C-4]": 358,
463
+ "[Nd]": 359,
464
+ "[Ti+]": 360,
465
+ "[IH]": 361,
466
+ "[N@+]": 362,
467
+ "[125I]": 363,
468
+ "[Eu]": 364,
469
+ "[Sn+3]": 365,
470
+ "[Nb]": 366,
471
+ "[Er+3]": 367,
472
+ "[123I-]": 368,
473
+ "[14c]": 369,
474
+ "%17": 370,
475
+ "[SnH2]": 371,
476
+ "[YH]": 372,
477
+ "[Sb+5]": 373,
478
+ "[Pr+3]": 374,
479
+ "[Ir+]": 375,
480
+ "[N+3]": 376,
481
+ "[AlH2]": 377,
482
+ "[19F]": 378,
483
+ "%18": 379,
484
+ "[Tb]": 380,
485
+ "[14CH]": 381,
486
+ "[Mo+4]": 382,
487
+ "[Si+]": 383,
488
+ "[BH]": 384,
489
+ "[Be]": 385,
490
+ "[Rb]": 386,
491
+ "[pH]": 387,
492
+ "%19": 388,
493
+ "%20": 389,
494
+ "[Xe]": 390,
495
+ "[Ir-]": 391,
496
+ "[Be+2]": 392,
497
+ "[C+4]": 393,
498
+ "[RuH2]": 394,
499
+ "[15NH]": 395,
500
+ "[U+2]": 396,
501
+ "[Au-]": 397,
502
+ "%21": 398,
503
+ "%22": 399,
504
+ "[Au+]": 400,
505
+ "[15n]": 401,
506
+ "[Al+2]": 402,
507
+ "[Tb+3]": 403,
508
+ "[15N]": 404,
509
+ "[V+3]": 405,
510
+ "[W+6]": 406,
511
+ "[14CH3]": 407,
512
+ "[Cr+4]": 408,
513
+ "[ClH+]": 409,
514
+ "b": 410,
515
+ "[Ti+6]": 411,
516
+ "[Nd+]": 412,
517
+ "[Zr+]": 413,
518
+ "[PH2+]": 414,
519
+ "[Fm]": 415,
520
+ "[N@H+]": 416,
521
+ "[RuH]": 417,
522
+ "[Dy+3]": 418,
523
+ "%23": 419,
524
+ "[Hf+3]": 420,
525
+ "[W+4]": 421,
526
+ "[11C]": 422,
527
+ "[13CH]": 423,
528
+ "[Er]": 424,
529
+ "[124I]": 425,
530
+ "[LaH]": 426,
531
+ "[F]": 427,
532
+ "[siH]": 428,
533
+ "[Ga+]": 429,
534
+ "[Cm]": 430,
535
+ "[GeH3]": 431,
536
+ "[IH-]": 432,
537
+ "[U+6]": 433,
538
+ "[SeH+]": 434,
539
+ "[32P]": 435,
540
+ "[SeH-]": 436,
541
+ "[Pt-]": 437,
542
+ "[Ir+2]": 438,
543
+ "[se+]": 439,
544
+ "[U]": 440,
545
+ "[F+]": 441,
546
+ "[BH2]": 442,
547
+ "[As+]": 443,
548
+ "[Cf]": 444,
549
+ "[ClH2+]": 445,
550
+ "[Ni+]": 446,
551
+ "[TeH3]": 447,
552
+ "[SbH2]": 448,
553
+ "[Ag+3]": 449,
554
+ "%24": 450,
555
+ "[18O]": 451,
556
+ "[PH4]": 452,
557
+ "[Os+2]": 453,
558
+ "[Na-]": 454,
559
+ "[Sb+2]": 455,
560
+ "[V+4]": 456,
561
+ "[Ho+3]": 457,
562
+ "[68Ga]": 458,
563
+ "[PH-]": 459,
564
+ "[Bi+2]": 460,
565
+ "[Ce+2]": 461,
566
+ "[Pd+3]": 462,
567
+ "[99Tc]": 463,
568
+ "[13C@@H]": 464,
569
+ "[Fe+6]": 465,
570
+ "[c]": 466,
571
+ "[GeH2]": 467,
572
+ "[10B]": 468,
573
+ "[Cu+3]": 469,
574
+ "[Mo+2]": 470,
575
+ "[Cr+]": 471,
576
+ "[Pd+4]": 472,
577
+ "[Dy]": 473,
578
+ "[AsH]": 474,
579
+ "[Ba+]": 475,
580
+ "[SeH2]": 476,
581
+ "[In+]": 477,
582
+ "[TeH2]": 478,
583
+ "[BrH+]": 479,
584
+ "[14cH]": 480,
585
+ "[W+]": 481,
586
+ "[13C@H]": 482,
587
+ "[AsH2]": 483,
588
+ "[In+2]": 484,
589
+ "[N+2]": 485,
590
+ "[N@@H+]": 486,
591
+ "[SbH]": 487,
592
+ "[60Co]": 488,
593
+ "[AsH4+]": 489,
594
+ "[AsH3]": 490,
595
+ "[18OH]": 491,
596
+ "[Ru-2]": 492,
597
+ "[Na-2]": 493,
598
+ "[CuH2]": 494,
599
+ "[31P]": 495,
600
+ "[Ti+5]": 496,
601
+ "[35S]": 497,
602
+ "[P@@H]": 498,
603
+ "[ArH]": 499,
604
+ "[Co+]": 500,
605
+ "[Zr-2]": 501,
606
+ "[BH2-]": 502,
607
+ "[131I]": 503,
608
+ "[SH5]": 504,
609
+ "[VH]": 505,
610
+ "[B+2]": 506,
611
+ "[Yb+2]": 507,
612
+ "[14C@H]": 508,
613
+ "[211At]": 509,
614
+ "[NH3+2]": 510,
615
+ "[IrH]": 511,
616
+ "[IrH2]": 512,
617
+ "[Rh-]": 513,
618
+ "[Cr-]": 514,
619
+ "[Sb+]": 515,
620
+ "[Ni+3]": 516,
621
+ "[TaH3]": 517,
622
+ "[Tl+2]": 518,
623
+ "[64Cu]": 519,
624
+ "[Tc]": 520,
625
+ "[Cd+]": 521,
626
+ "[1H]": 522,
627
+ "[15nH]": 523,
628
+ "[AlH2+]": 524,
629
+ "[FH+2]": 525,
630
+ "[BiH3]": 526,
631
+ "[Ru-]": 527,
632
+ "[Mo+6]": 528,
633
+ "[AsH+]": 529,
634
+ "[BaH2]": 530,
635
+ "[BaH]": 531,
636
+ "[Fe+4]": 532,
637
+ "[229Th]": 533,
638
+ "[Th+4]": 534,
639
+ "[As+3]": 535,
640
+ "[NH+3]": 536,
641
+ "[P@H]": 537,
642
+ "[Li-]": 538,
643
+ "[7NaH]": 539,
644
+ "[Bi+]": 540,
645
+ "[PtH+2]": 541,
646
+ "[p-]": 542,
647
+ "[Re+5]": 543,
648
+ "[NiH]": 544,
649
+ "[Ni-]": 545,
650
+ "[Xe+]": 546,
651
+ "[Ca+]": 547,
652
+ "[11c]": 548,
653
+ "[Rh+4]": 549,
654
+ "[AcH]": 550,
655
+ "[HeH]": 551,
656
+ "[Sc+2]": 552,
657
+ "[Mn+]": 553,
658
+ "[UH]": 554,
659
+ "[14CH2]": 555,
660
+ "[SiH4+]": 556,
661
+ "[18OH2]": 557,
662
+ "[Ac-]": 558,
663
+ "[Re+4]": 559,
664
+ "[118Sn]": 560,
665
+ "[153Sm]": 561,
666
+ "[P+2]": 562,
667
+ "[9CH]": 563,
668
+ "[9CH3]": 564,
669
+ "[Y-]": 565,
670
+ "[NiH2]": 566,
671
+ "[Si+2]": 567,
672
+ "[Mn+6]": 568,
673
+ "[ZrH2]": 569,
674
+ "[C-2]": 570,
675
+ "[Bi+5]": 571,
676
+ "[24NaH]": 572,
677
+ "[Fr]": 573,
678
+ "[15CH]": 574,
679
+ "[Se+]": 575,
680
+ "[At]": 576,
681
+ "[P-3]": 577,
682
+ "[124I-]": 578,
683
+ "[CuH2-]": 579,
684
+ "[Nb+4]": 580,
685
+ "[Nb+3]": 581,
686
+ "[MgH]": 582,
687
+ "[Ir+4]": 583,
688
+ "[67Ga+3]": 584,
689
+ "[67Ga]": 585,
690
+ "[13N]": 586,
691
+ "[15OH2]": 587,
692
+ "[2NH]": 588,
693
+ "[Ho]": 589,
694
+ "[Cn]": 590
695
+ },
696
+ "merges": []
697
+ }
698
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "[CLS]",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "do_lower_case": false,
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
+ "full_tokenizer_file": null,
30
+ "mask_token": {
31
+ "__type": "AddedToken",
32
+ "content": "[MASK]",
33
+ "lstrip": true,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ "max_len": 512,
39
+ "name_or_path": "/content/outputs/best_model",
40
+ "pad_token": {
41
+ "__type": "AddedToken",
42
+ "content": "[PAD]",
43
+ "lstrip": false,
44
+ "normalized": true,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "sep_token": {
49
+ "__type": "AddedToken",
50
+ "content": "[SEP]",
51
+ "lstrip": false,
52
+ "normalized": true,
53
+ "rstrip": false,
54
+ "single_word": false
55
+ },
56
+ "special_tokens_map_file": "/content/drive/My Drive/Project De Novo/Molecule Transformer/SMILES_tokenized_PubChem_shard00_100k/checkpoint-60000/special_tokens_map.json",
57
+ "tokenizer_class": "RobertaTokenizer",
58
+ "trim_offsets": true,
59
+ "unk_token": {
60
+ "__type": "AddedToken",
61
+ "content": "[UNK]",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ }
67
+ }
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"[PAD]":0,"[unused1]":1,"[unused2]":2,"[unused3]":3,"[unused4]":4,"[unused5]":5,"[unused6]":6,"[unused7]":7,"[unused8]":8,"[unused9]":9,"[unused10]":10,"[UNK]":11,"[CLS]":12,"[SEP]":13,"[MASK]":14,"c":15,"C":16,"(":17,")":18,"O":19,"1":20,"2":21,"=":22,"N":23,".":24,"n":25,"3":26,"F":27,"Cl":28,">>":29,"~":30,"-":31,"4":32,"[C@H]":33,"S":34,"[C@@H]":35,"[O-]":36,"Br":37,"#":38,"/":39,"[nH]":40,"[N+]":41,"s":42,"5":43,"o":44,"P":45,"[Na+]":46,"[Si]":47,"I":48,"[Na]":49,"[Pd]":50,"[K+]":51,"[K]":52,"[P]":53,"B":54,"[C@]":55,"[C@@]":56,"[Cl-]":57,"6":58,"[OH-]":59,"\\":60,"[N-]":61,"[Li]":62,"[H]":63,"[2H]":64,"[NH4+]":65,"[c-]":66,"[P-]":67,"[Cs+]":68,"[Li+]":69,"[Cs]":70,"[NaH]":71,"[H-]":72,"[O+]":73,"[BH4-]":74,"[Cu]":75,"7":76,"[Mg]":77,"[Fe+2]":78,"[n+]":79,"[Sn]":80,"[BH-]":81,"[Pd+2]":82,"[CH]":83,"[I-]":84,"[Br-]":85,"[C-]":86,"[Zn]":87,"[B-]":88,"[F-]":89,"[Al]":90,"[P+]":91,"[BH3-]":92,"[Fe]":93,"[C]":94,"[AlH4]":95,"[Ni]":96,"[SiH]":97,"8":98,"[Cu+2]":99,"[Mn]":100,"[AlH]":101,"[nH+]":102,"[AlH4-]":103,"[O-2]":104,"[Cr]":105,"[Mg+2]":106,"[NH3+]":107,"[S@]":108,"[Pt]":109,"[Al+3]":110,"[S@@]":111,"[S-]":112,"[Ti]":113,"[Zn+2]":114,"[PH]":115,"[NH2+]":116,"[Ru]":117,"[Ag+]":118,"[S+]":119,"[I+3]":120,"[NH+]":121,"[Ca+2]":122,"[Ag]":123,"9":124,"[Os]":125,"[Se]":126,"[SiH2]":127,"[Ca]":128,"[Ti+4]":129,"[Ac]":130,"[Cu+]":131,"[S]":132,"[Rh]":133,"[Cl+3]":134,"[cH-]":135,"[Zn+]":136,"[O]":137,"[Cl+]":138,"[SH]":139,"[H+]":140,"[Pd+]":141,"[se]":142,"[PH+]":143,"[I]":144,"[Pt+2]":145,"[C+]":146,"[Mg+]":147,"[Hg]":148,"[W]":149,"[SnH]":150,"[SiH3]":151,"[Fe+3]":152,"[NH]":153,"[Mo]":154,"[CH2+]":155,"%10":156,"[CH2-]":157,"[CH2]":158,"[n-]":159,"[Ce+4]":160,"[NH-]":161,"[Co]":162,"[I+]":163,"[PH2]":164,"[Pt+4]":165,"[Ce]":166,"[B]":167,"[Sn+2]":168,"[Ba+2]":169,"%11":170,"[Fe-3]":171,"[18F]":172,"[SH-]":173,"[Pb+2]":174,"[Os-2]":175,"[Zr+4]":176,"[N]":177,"[Ir]":178,"[Bi]":179,"[Ni+2]":180,"[P@]":181,"[Co+2]":182,"[s+]":183,"[As]":184,"[P+3]":185,"[Hg+2]":186,"[Yb+3]":187,"[CH-]":188,"[Zr+2]":189,"[Mn+2]":190,"[CH+]":191,"[In]":192,"[KH]":193,"[Ce+3]":194,"[Zr]":195,"[AlH2-]":196,"[OH2+]":197,"[Ti+3]":198,"[Rh+2]":199,"[Sb]":200,"[S-2]":201,"%12":202,"[P@@]":203,"[Si@H]":204,"[Mn+4]":205,"p":206,"[Ba]":207,"[NH2-]":208,"[Ge]":209,"[Pb+4]":210,"[Cr+3]":211,"[Au]":212,"[LiH]":213,"[Sc+3]":214,"[o+]":215,"[Rh-3]":216,"%13":217,"[Br]":218,"[Sb-]":219,"[S@+]":220,"[I+2]":221,"[Ar]":222,"[V]":223,"[Cu-]":224,"[Al-]":225,"[Te]":226,"[13c]":227,"[13C]":228,"[Cl]":229,"[PH4+]":230,"[SiH4]":231,"[te]":232,"[CH3-]":233,"[S@@+]":234,"[Rh+3]":235,"[SH+]":236,"[Bi+3]":237,"[Br+2]":238,"[La]":239,"[La+3]":240,"[Pt-2]":241,"[N@@]":242,"[PH3+]":243,"[N@]":244,"[Si+4]":245,"[Sr+2]":246,"[Al+]":247,"[Pb]":248,"[SeH]":249,"[Si-]":250,"[V+5]":251,"[Y+3]":252,"[Re]":253,"[Ru+]":254,"[Sm]":255,"*":256,"[3H]":257,"[NH2]":258,"[Ag-]":259,"[13CH3]":260,"[OH+]":261,"[Ru+3]":262,"[OH]":263,"[Gd+3]":264,"[13CH2]":265,"[In+3]":266,"[Si@@]":267,"[Si@]":268,"[Ti+2]":269,"[Sn+]":270,"[Cl+2]":271,"[AlH-]":272,"[Pd-2]":273,"[SnH3]":274,"[B+3]":275,"[Cu-2]":276,"[Nd+3]":277,"[Pb+3]":278,"[13cH]":279,"[Fe-4]":280,"[Ga]":281,"[Sn+4]":282,"[Hg+]":283,"[11CH3]":284,"[Hf]":285,"[Pr]":286,"[Y]":287,"[S+2]":288,"[Cd]":289,"[Cr+6]":290,"[Zr+3]":291,"[Rh+]":292,"[CH3]":293,"[N-3]":294,"[Hf+2]":295,"[Th]":296,"[Sb+3]":297,"%14":298,"[Cr+2]":299,"[Ru+2]":300,"[Hf+4]":301,"[14C]":302,"[Ta]":303,"[Tl+]":304,"[B+]":305,"[Os+4]":306,"[PdH2]":307,"[Pd-]":308,"[Cd+2]":309,"[Co+3]":310,"[S+4]":311,"[Nb+5]":312,"[123I]":313,"[c+]":314,"[Rb+]":315,"[V+2]":316,"[CH3+]":317,"[Ag+2]":318,"[cH+]":319,"[Mn+3]":320,"[Se-]":321,"[As-]":322,"[Eu+3]":323,"[SH2]":324,"[Sm+3]":325,"[IH+]":326,"%15":327,"[OH3+]":328,"[PH3]":329,"[IH2+]":330,"[SH2+]":331,"[Ir+3]":332,"[AlH3]":333,"[Sc]":334,"[Yb]":335,"[15NH2]":336,"[Lu]":337,"[sH+]":338,"[Gd]":339,"[18F-]":340,"[SH3+]":341,"[SnH4]":342,"[TeH]":343,"[Si@@H]":344,"[Ga+3]":345,"[CaH2]":346,"[Tl]":347,"[Ta+5]":348,"[GeH]":349,"[Br+]":350,"[Sr]":351,"[Tl+3]":352,"[Sm+2]":353,"[PH5]":354,"%16":355,"[N@@+]":356,"[Au+3]":357,"[C-4]":358,"[Nd]":359,"[Ti+]":360,"[IH]":361,"[N@+]":362,"[125I]":363,"[Eu]":364,"[Sn+3]":365,"[Nb]":366,"[Er+3]":367,"[123I-]":368,"[14c]":369,"%17":370,"[SnH2]":371,"[YH]":372,"[Sb+5]":373,"[Pr+3]":374,"[Ir+]":375,"[N+3]":376,"[AlH2]":377,"[19F]":378,"%18":379,"[Tb]":380,"[14CH]":381,"[Mo+4]":382,"[Si+]":383,"[BH]":384,"[Be]":385,"[Rb]":386,"[pH]":387,"%19":388,"%20":389,"[Xe]":390,"[Ir-]":391,"[Be+2]":392,"[C+4]":393,"[RuH2]":394,"[15NH]":395,"[U+2]":396,"[Au-]":397,"%21":398,"%22":399,"[Au+]":400,"[15n]":401,"[Al+2]":402,"[Tb+3]":403,"[15N]":404,"[V+3]":405,"[W+6]":406,"[14CH3]":407,"[Cr+4]":408,"[ClH+]":409,"b":410,"[Ti+6]":411,"[Nd+]":412,"[Zr+]":413,"[PH2+]":414,"[Fm]":415,"[N@H+]":416,"[RuH]":417,"[Dy+3]":418,"%23":419,"[Hf+3]":420,"[W+4]":421,"[11C]":422,"[13CH]":423,"[Er]":424,"[124I]":425,"[LaH]":426,"[F]":427,"[siH]":428,"[Ga+]":429,"[Cm]":430,"[GeH3]":431,"[IH-]":432,"[U+6]":433,"[SeH+]":434,"[32P]":435,"[SeH-]":436,"[Pt-]":437,"[Ir+2]":438,"[se+]":439,"[U]":440,"[F+]":441,"[BH2]":442,"[As+]":443,"[Cf]":444,"[ClH2+]":445,"[Ni+]":446,"[TeH3]":447,"[SbH2]":448,"[Ag+3]":449,"%24":450,"[18O]":451,"[PH4]":452,"[Os+2]":453,"[Na-]":454,"[Sb+2]":455,"[V+4]":456,"[Ho+3]":457,"[68Ga]":458,"[PH-]":459,"[Bi+2]":460,"[Ce+2]":461,"[Pd+3]":462,"[99Tc]":463,"[13C@@H]":464,"[Fe+6]":465,"[c]":466,"[GeH2]":467,"[10B]":468,"[Cu+3]":469,"[Mo+2]":470,"[Cr+]":471,"[Pd+4]":472,"[Dy]":473,"[AsH]":474,"[Ba+]":475,"[SeH2]":476,"[In+]":477,"[TeH2]":478,"[BrH+]":479,"[14cH]":480,"[W+]":481,"[13C@H]":482,"[AsH2]":483,"[In+2]":484,"[N+2]":485,"[N@@H+]":486,"[SbH]":487,"[60Co]":488,"[AsH4+]":489,"[AsH3]":490,"[18OH]":491,"[Ru-2]":492,"[Na-2]":493,"[CuH2]":494,"[31P]":495,"[Ti+5]":496,"[35S]":497,"[P@@H]":498,"[ArH]":499,"[Co+]":500,"[Zr-2]":501,"[BH2-]":502,"[131I]":503,"[SH5]":504,"[VH]":505,"[B+2]":506,"[Yb+2]":507,"[14C@H]":508,"[211At]":509,"[NH3+2]":510,"[IrH]":511,"[IrH2]":512,"[Rh-]":513,"[Cr-]":514,"[Sb+]":515,"[Ni+3]":516,"[TaH3]":517,"[Tl+2]":518,"[64Cu]":519,"[Tc]":520,"[Cd+]":521,"[1H]":522,"[15nH]":523,"[AlH2+]":524,"[FH+2]":525,"[BiH3]":526,"[Ru-]":527,"[Mo+6]":528,"[AsH+]":529,"[BaH2]":530,"[BaH]":531,"[Fe+4]":532,"[229Th]":533,"[Th+4]":534,"[As+3]":535,"[NH+3]":536,"[P@H]":537,"[Li-]":538,"[7NaH]":539,"[Bi+]":540,"[PtH+2]":541,"[p-]":542,"[Re+5]":543,"[NiH]":544,"[Ni-]":545,"[Xe+]":546,"[Ca+]":547,"[11c]":548,"[Rh+4]":549,"[AcH]":550,"[HeH]":551,"[Sc+2]":552,"[Mn+]":553,"[UH]":554,"[14CH2]":555,"[SiH4+]":556,"[18OH2]":557,"[Ac-]":558,"[Re+4]":559,"[118Sn]":560,"[153Sm]":561,"[P+2]":562,"[9CH]":563,"[9CH3]":564,"[Y-]":565,"[NiH2]":566,"[Si+2]":567,"[Mn+6]":568,"[ZrH2]":569,"[C-2]":570,"[Bi+5]":571,"[24NaH]":572,"[Fr]":573,"[15CH]":574,"[Se+]":575,"[At]":576,"[P-3]":577,"[124I-]":578,"[CuH2-]":579,"[Nb+4]":580,"[Nb+3]":581,"[MgH]":582,"[Ir+4]":583,"[67Ga+3]":584,"[67Ga]":585,"[13N]":586,"[15OH2]":587,"[2NH]":588,"[Ho]":589,"[Cn]":590}