Fill-Mask
Transformers
Safetensors
roberta
eacortes commited on
Commit
b2043cc
·
verified ·
1 Parent(s): 097cb72

Upload model and tokenizer files

Browse files
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "training_output/chemberta_pubchem_10m/checkpoint-24000",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.11,
7
+ "bos_token_id": 1,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.15,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 520,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 6,
20
+ "pad_token_id": 3,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.48.2",
24
+ "type_vocab_size": 1,
25
+ "use_cache": false,
26
+ "vocab_size": 581
27
+ }
merges.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ #version: 0.2
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cefeb10f0f59f5b9968102fac4ff0fc5aa1afbf09c746a48cfd2ac92d823b695
3
+ size 175883708
special_tokens_map.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eos_token": "</s>",
11
+ "mask_token": {
12
+ "content": "<mask>",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "pad_token": "<pad>",
19
+ "sep_token": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": "<unk>"
27
+ }
tokenizer.json ADDED
@@ -0,0 +1,672 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<unk>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": true,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<s>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": true,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "</s>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": true,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<pad>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": true,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "<mask>",
45
+ "single_word": false,
46
+ "lstrip": true,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ }
51
+ ],
52
+ "normalizer": null,
53
+ "pre_tokenizer": {
54
+ "type": "ByteLevel",
55
+ "add_prefix_space": false,
56
+ "trim_offsets": true,
57
+ "use_regex": true
58
+ },
59
+ "post_processor": {
60
+ "type": "RobertaProcessing",
61
+ "sep": [
62
+ "</s>",
63
+ 2
64
+ ],
65
+ "cls": [
66
+ "<s>",
67
+ 1
68
+ ],
69
+ "trim_offsets": true,
70
+ "add_prefix_space": false
71
+ },
72
+ "decoder": {
73
+ "type": "ByteLevel",
74
+ "add_prefix_space": true,
75
+ "trim_offsets": true,
76
+ "use_regex": true
77
+ },
78
+ "model": {
79
+ "type": "BPE",
80
+ "dropout": null,
81
+ "unk_token": null,
82
+ "continuing_subword_prefix": "",
83
+ "end_of_word_suffix": "",
84
+ "fuse_unk": false,
85
+ "byte_fallback": false,
86
+ "ignore_merges": false,
87
+ "vocab": {
88
+ "<unk>": 0,
89
+ "<s>": 1,
90
+ "</s>": 2,
91
+ "<pad>": 3,
92
+ "<mask>": 4,
93
+ "c": 5,
94
+ "C": 6,
95
+ "(": 7,
96
+ ")": 8,
97
+ "O": 9,
98
+ "1": 10,
99
+ "2": 11,
100
+ "=": 12,
101
+ "N": 13,
102
+ ".": 14,
103
+ "n": 15,
104
+ "3": 16,
105
+ "F": 17,
106
+ "Cl": 18,
107
+ ">>": 19,
108
+ "~": 20,
109
+ "-": 21,
110
+ "4": 22,
111
+ "[C@H]": 23,
112
+ "S": 24,
113
+ "[C@@H]": 25,
114
+ "[O-]": 26,
115
+ "Br": 27,
116
+ "#": 28,
117
+ "/": 29,
118
+ "[nH]": 30,
119
+ "[N+]": 31,
120
+ "s": 32,
121
+ "5": 33,
122
+ "o": 34,
123
+ "P": 35,
124
+ "[Na+]": 36,
125
+ "[Si]": 37,
126
+ "I": 38,
127
+ "[Na]": 39,
128
+ "[Pd]": 40,
129
+ "[K+]": 41,
130
+ "[K]": 42,
131
+ "[P]": 43,
132
+ "B": 44,
133
+ "[C@]": 45,
134
+ "[C@@]": 46,
135
+ "[Cl-]": 47,
136
+ "6": 48,
137
+ "[OH-]": 49,
138
+ "\\": 50,
139
+ "[N-]": 51,
140
+ "[Li]": 52,
141
+ "[H]": 53,
142
+ "[2H]": 54,
143
+ "[NH4+]": 55,
144
+ "[c-]": 56,
145
+ "[P-]": 57,
146
+ "[Cs+]": 58,
147
+ "[Li+]": 59,
148
+ "[Cs]": 60,
149
+ "[NaH]": 61,
150
+ "[H-]": 62,
151
+ "[O+]": 63,
152
+ "[BH4-]": 64,
153
+ "[Cu]": 65,
154
+ "7": 66,
155
+ "[Mg]": 67,
156
+ "[Fe+2]": 68,
157
+ "[n+]": 69,
158
+ "[Sn]": 70,
159
+ "[BH-]": 71,
160
+ "[Pd+2]": 72,
161
+ "[CH]": 73,
162
+ "[I-]": 74,
163
+ "[Br-]": 75,
164
+ "[C-]": 76,
165
+ "[Zn]": 77,
166
+ "[B-]": 78,
167
+ "[F-]": 79,
168
+ "[Al]": 80,
169
+ "[P+]": 81,
170
+ "[BH3-]": 82,
171
+ "[Fe]": 83,
172
+ "[C]": 84,
173
+ "[AlH4]": 85,
174
+ "[Ni]": 86,
175
+ "[SiH]": 87,
176
+ "8": 88,
177
+ "[Cu+2]": 89,
178
+ "[Mn]": 90,
179
+ "[AlH]": 91,
180
+ "[nH+]": 92,
181
+ "[AlH4-]": 93,
182
+ "[O-2]": 94,
183
+ "[Cr]": 95,
184
+ "[Mg+2]": 96,
185
+ "[NH3+]": 97,
186
+ "[S@]": 98,
187
+ "[Pt]": 99,
188
+ "[Al+3]": 100,
189
+ "[S@@]": 101,
190
+ "[S-]": 102,
191
+ "[Ti]": 103,
192
+ "[Zn+2]": 104,
193
+ "[PH]": 105,
194
+ "[NH2+]": 106,
195
+ "[Ru]": 107,
196
+ "[Ag+]": 108,
197
+ "[S+]": 109,
198
+ "[I+3]": 110,
199
+ "[NH+]": 111,
200
+ "[Ca+2]": 112,
201
+ "[Ag]": 113,
202
+ "9": 114,
203
+ "[Os]": 115,
204
+ "[Se]": 116,
205
+ "[SiH2]": 117,
206
+ "[Ca]": 118,
207
+ "[Ti+4]": 119,
208
+ "[Ac]": 120,
209
+ "[Cu+]": 121,
210
+ "[S]": 122,
211
+ "[Rh]": 123,
212
+ "[Cl+3]": 124,
213
+ "[cH-]": 125,
214
+ "[Zn+]": 126,
215
+ "[O]": 127,
216
+ "[Cl+]": 128,
217
+ "[SH]": 129,
218
+ "[H+]": 130,
219
+ "[Pd+]": 131,
220
+ "[se]": 132,
221
+ "[PH+]": 133,
222
+ "[I]": 134,
223
+ "[Pt+2]": 135,
224
+ "[C+]": 136,
225
+ "[Mg+]": 137,
226
+ "[Hg]": 138,
227
+ "[W]": 139,
228
+ "[SnH]": 140,
229
+ "[SiH3]": 141,
230
+ "[Fe+3]": 142,
231
+ "[NH]": 143,
232
+ "[Mo]": 144,
233
+ "[CH2+]": 145,
234
+ "%10": 146,
235
+ "[CH2-]": 147,
236
+ "[CH2]": 148,
237
+ "[n-]": 149,
238
+ "[Ce+4]": 150,
239
+ "[NH-]": 151,
240
+ "[Co]": 152,
241
+ "[I+]": 153,
242
+ "[PH2]": 154,
243
+ "[Pt+4]": 155,
244
+ "[Ce]": 156,
245
+ "[B]": 157,
246
+ "[Sn+2]": 158,
247
+ "[Ba+2]": 159,
248
+ "%11": 160,
249
+ "[Fe-3]": 161,
250
+ "[18F]": 162,
251
+ "[SH-]": 163,
252
+ "[Pb+2]": 164,
253
+ "[Os-2]": 165,
254
+ "[Zr+4]": 166,
255
+ "[N]": 167,
256
+ "[Ir]": 168,
257
+ "[Bi]": 169,
258
+ "[Ni+2]": 170,
259
+ "[P@]": 171,
260
+ "[Co+2]": 172,
261
+ "[s+]": 173,
262
+ "[As]": 174,
263
+ "[P+3]": 175,
264
+ "[Hg+2]": 176,
265
+ "[Yb+3]": 177,
266
+ "[CH-]": 178,
267
+ "[Zr+2]": 179,
268
+ "[Mn+2]": 180,
269
+ "[CH+]": 181,
270
+ "[In]": 182,
271
+ "[KH]": 183,
272
+ "[Ce+3]": 184,
273
+ "[Zr]": 185,
274
+ "[AlH2-]": 186,
275
+ "[OH2+]": 187,
276
+ "[Ti+3]": 188,
277
+ "[Rh+2]": 189,
278
+ "[Sb]": 190,
279
+ "[S-2]": 191,
280
+ "%12": 192,
281
+ "[P@@]": 193,
282
+ "[Si@H]": 194,
283
+ "[Mn+4]": 195,
284
+ "p": 196,
285
+ "[Ba]": 197,
286
+ "[NH2-]": 198,
287
+ "[Ge]": 199,
288
+ "[Pb+4]": 200,
289
+ "[Cr+3]": 201,
290
+ "[Au]": 202,
291
+ "[LiH]": 203,
292
+ "[Sc+3]": 204,
293
+ "[o+]": 205,
294
+ "[Rh-3]": 206,
295
+ "%13": 207,
296
+ "[Br]": 208,
297
+ "[Sb-]": 209,
298
+ "[S@+]": 210,
299
+ "[I+2]": 211,
300
+ "[Ar]": 212,
301
+ "[V]": 213,
302
+ "[Cu-]": 214,
303
+ "[Al-]": 215,
304
+ "[Te]": 216,
305
+ "[13c]": 217,
306
+ "[13C]": 218,
307
+ "[Cl]": 219,
308
+ "[PH4+]": 220,
309
+ "[SiH4]": 221,
310
+ "[te]": 222,
311
+ "[CH3-]": 223,
312
+ "[S@@+]": 224,
313
+ "[Rh+3]": 225,
314
+ "[SH+]": 226,
315
+ "[Bi+3]": 227,
316
+ "[Br+2]": 228,
317
+ "[La]": 229,
318
+ "[La+3]": 230,
319
+ "[Pt-2]": 231,
320
+ "[N@@]": 232,
321
+ "[PH3+]": 233,
322
+ "[N@]": 234,
323
+ "[Si+4]": 235,
324
+ "[Sr+2]": 236,
325
+ "[Al+]": 237,
326
+ "[Pb]": 238,
327
+ "[SeH]": 239,
328
+ "[Si-]": 240,
329
+ "[V+5]": 241,
330
+ "[Y+3]": 242,
331
+ "[Re]": 243,
332
+ "[Ru+]": 244,
333
+ "[Sm]": 245,
334
+ "*": 246,
335
+ "[3H]": 247,
336
+ "[NH2]": 248,
337
+ "[Ag-]": 249,
338
+ "[13CH3]": 250,
339
+ "[OH+]": 251,
340
+ "[Ru+3]": 252,
341
+ "[OH]": 253,
342
+ "[Gd+3]": 254,
343
+ "[13CH2]": 255,
344
+ "[In+3]": 256,
345
+ "[Si@@]": 257,
346
+ "[Si@]": 258,
347
+ "[Ti+2]": 259,
348
+ "[Sn+]": 260,
349
+ "[Cl+2]": 261,
350
+ "[AlH-]": 262,
351
+ "[Pd-2]": 263,
352
+ "[SnH3]": 264,
353
+ "[B+3]": 265,
354
+ "[Cu-2]": 266,
355
+ "[Nd+3]": 267,
356
+ "[Pb+3]": 268,
357
+ "[13cH]": 269,
358
+ "[Fe-4]": 270,
359
+ "[Ga]": 271,
360
+ "[Sn+4]": 272,
361
+ "[Hg+]": 273,
362
+ "[11CH3]": 274,
363
+ "[Hf]": 275,
364
+ "[Pr]": 276,
365
+ "[Y]": 277,
366
+ "[S+2]": 278,
367
+ "[Cd]": 279,
368
+ "[Cr+6]": 280,
369
+ "[Zr+3]": 281,
370
+ "[Rh+]": 282,
371
+ "[CH3]": 283,
372
+ "[N-3]": 284,
373
+ "[Hf+2]": 285,
374
+ "[Th]": 286,
375
+ "[Sb+3]": 287,
376
+ "%14": 288,
377
+ "[Cr+2]": 289,
378
+ "[Ru+2]": 290,
379
+ "[Hf+4]": 291,
380
+ "[14C]": 292,
381
+ "[Ta]": 293,
382
+ "[Tl+]": 294,
383
+ "[B+]": 295,
384
+ "[Os+4]": 296,
385
+ "[PdH2]": 297,
386
+ "[Pd-]": 298,
387
+ "[Cd+2]": 299,
388
+ "[Co+3]": 300,
389
+ "[S+4]": 301,
390
+ "[Nb+5]": 302,
391
+ "[123I]": 303,
392
+ "[c+]": 304,
393
+ "[Rb+]": 305,
394
+ "[V+2]": 306,
395
+ "[CH3+]": 307,
396
+ "[Ag+2]": 308,
397
+ "[cH+]": 309,
398
+ "[Mn+3]": 310,
399
+ "[Se-]": 311,
400
+ "[As-]": 312,
401
+ "[Eu+3]": 313,
402
+ "[SH2]": 314,
403
+ "[Sm+3]": 315,
404
+ "[IH+]": 316,
405
+ "%15": 317,
406
+ "[OH3+]": 318,
407
+ "[PH3]": 319,
408
+ "[IH2+]": 320,
409
+ "[SH2+]": 321,
410
+ "[Ir+3]": 322,
411
+ "[AlH3]": 323,
412
+ "[Sc]": 324,
413
+ "[Yb]": 325,
414
+ "[15NH2]": 326,
415
+ "[Lu]": 327,
416
+ "[sH+]": 328,
417
+ "[Gd]": 329,
418
+ "[18F-]": 330,
419
+ "[SH3+]": 331,
420
+ "[SnH4]": 332,
421
+ "[TeH]": 333,
422
+ "[Si@@H]": 334,
423
+ "[Ga+3]": 335,
424
+ "[CaH2]": 336,
425
+ "[Tl]": 337,
426
+ "[Ta+5]": 338,
427
+ "[GeH]": 339,
428
+ "[Br+]": 340,
429
+ "[Sr]": 341,
430
+ "[Tl+3]": 342,
431
+ "[Sm+2]": 343,
432
+ "[PH5]": 344,
433
+ "%16": 345,
434
+ "[N@@+]": 346,
435
+ "[Au+3]": 347,
436
+ "[C-4]": 348,
437
+ "[Nd]": 349,
438
+ "[Ti+]": 350,
439
+ "[IH]": 351,
440
+ "[N@+]": 352,
441
+ "[125I]": 353,
442
+ "[Eu]": 354,
443
+ "[Sn+3]": 355,
444
+ "[Nb]": 356,
445
+ "[Er+3]": 357,
446
+ "[123I-]": 358,
447
+ "[14c]": 359,
448
+ "%17": 360,
449
+ "[SnH2]": 361,
450
+ "[YH]": 362,
451
+ "[Sb+5]": 363,
452
+ "[Pr+3]": 364,
453
+ "[Ir+]": 365,
454
+ "[N+3]": 366,
455
+ "[AlH2]": 367,
456
+ "[19F]": 368,
457
+ "%18": 369,
458
+ "[Tb]": 370,
459
+ "[14CH]": 371,
460
+ "[Mo+4]": 372,
461
+ "[Si+]": 373,
462
+ "[BH]": 374,
463
+ "[Be]": 375,
464
+ "[Rb]": 376,
465
+ "[pH]": 377,
466
+ "%19": 378,
467
+ "%20": 379,
468
+ "[Xe]": 380,
469
+ "[Ir-]": 381,
470
+ "[Be+2]": 382,
471
+ "[C+4]": 383,
472
+ "[RuH2]": 384,
473
+ "[15NH]": 385,
474
+ "[U+2]": 386,
475
+ "[Au-]": 387,
476
+ "%21": 388,
477
+ "%22": 389,
478
+ "[Au+]": 390,
479
+ "[15n]": 391,
480
+ "[Al+2]": 392,
481
+ "[Tb+3]": 393,
482
+ "[15N]": 394,
483
+ "[V+3]": 395,
484
+ "[W+6]": 396,
485
+ "[14CH3]": 397,
486
+ "[Cr+4]": 398,
487
+ "[ClH+]": 399,
488
+ "b": 400,
489
+ "[Ti+6]": 401,
490
+ "[Nd+]": 402,
491
+ "[Zr+]": 403,
492
+ "[PH2+]": 404,
493
+ "[Fm]": 405,
494
+ "[N@H+]": 406,
495
+ "[RuH]": 407,
496
+ "[Dy+3]": 408,
497
+ "%23": 409,
498
+ "[Hf+3]": 410,
499
+ "[W+4]": 411,
500
+ "[11C]": 412,
501
+ "[13CH]": 413,
502
+ "[Er]": 414,
503
+ "[124I]": 415,
504
+ "[LaH]": 416,
505
+ "[F]": 417,
506
+ "[siH]": 418,
507
+ "[Ga+]": 419,
508
+ "[Cm]": 420,
509
+ "[GeH3]": 421,
510
+ "[IH-]": 422,
511
+ "[U+6]": 423,
512
+ "[SeH+]": 424,
513
+ "[32P]": 425,
514
+ "[SeH-]": 426,
515
+ "[Pt-]": 427,
516
+ "[Ir+2]": 428,
517
+ "[se+]": 429,
518
+ "[U]": 430,
519
+ "[F+]": 431,
520
+ "[BH2]": 432,
521
+ "[As+]": 433,
522
+ "[Cf]": 434,
523
+ "[ClH2+]": 435,
524
+ "[Ni+]": 436,
525
+ "[TeH3]": 437,
526
+ "[SbH2]": 438,
527
+ "[Ag+3]": 439,
528
+ "%24": 440,
529
+ "[18O]": 441,
530
+ "[PH4]": 442,
531
+ "[Os+2]": 443,
532
+ "[Na-]": 444,
533
+ "[Sb+2]": 445,
534
+ "[V+4]": 446,
535
+ "[Ho+3]": 447,
536
+ "[68Ga]": 448,
537
+ "[PH-]": 449,
538
+ "[Bi+2]": 450,
539
+ "[Ce+2]": 451,
540
+ "[Pd+3]": 452,
541
+ "[99Tc]": 453,
542
+ "[13C@@H]": 454,
543
+ "[Fe+6]": 455,
544
+ "[c]": 456,
545
+ "[GeH2]": 457,
546
+ "[10B]": 458,
547
+ "[Cu+3]": 459,
548
+ "[Mo+2]": 460,
549
+ "[Cr+]": 461,
550
+ "[Pd+4]": 462,
551
+ "[Dy]": 463,
552
+ "[AsH]": 464,
553
+ "[Ba+]": 465,
554
+ "[SeH2]": 466,
555
+ "[In+]": 467,
556
+ "[TeH2]": 468,
557
+ "[BrH+]": 469,
558
+ "[14cH]": 470,
559
+ "[W+]": 471,
560
+ "[13C@H]": 472,
561
+ "[AsH2]": 473,
562
+ "[In+2]": 474,
563
+ "[N+2]": 475,
564
+ "[N@@H+]": 476,
565
+ "[SbH]": 477,
566
+ "[60Co]": 478,
567
+ "[AsH4+]": 479,
568
+ "[AsH3]": 480,
569
+ "[18OH]": 481,
570
+ "[Ru-2]": 482,
571
+ "[Na-2]": 483,
572
+ "[CuH2]": 484,
573
+ "[31P]": 485,
574
+ "[Ti+5]": 486,
575
+ "[35S]": 487,
576
+ "[P@@H]": 488,
577
+ "[ArH]": 489,
578
+ "[Co+]": 490,
579
+ "[Zr-2]": 491,
580
+ "[BH2-]": 492,
581
+ "[131I]": 493,
582
+ "[SH5]": 494,
583
+ "[VH]": 495,
584
+ "[B+2]": 496,
585
+ "[Yb+2]": 497,
586
+ "[14C@H]": 498,
587
+ "[211At]": 499,
588
+ "[NH3+2]": 500,
589
+ "[IrH]": 501,
590
+ "[IrH2]": 502,
591
+ "[Rh-]": 503,
592
+ "[Cr-]": 504,
593
+ "[Sb+]": 505,
594
+ "[Ni+3]": 506,
595
+ "[TaH3]": 507,
596
+ "[Tl+2]": 508,
597
+ "[64Cu]": 509,
598
+ "[Tc]": 510,
599
+ "[Cd+]": 511,
600
+ "[1H]": 512,
601
+ "[15nH]": 513,
602
+ "[AlH2+]": 514,
603
+ "[FH+2]": 515,
604
+ "[BiH3]": 516,
605
+ "[Ru-]": 517,
606
+ "[Mo+6]": 518,
607
+ "[AsH+]": 519,
608
+ "[BaH2]": 520,
609
+ "[BaH]": 521,
610
+ "[Fe+4]": 522,
611
+ "[229Th]": 523,
612
+ "[Th+4]": 524,
613
+ "[As+3]": 525,
614
+ "[NH+3]": 526,
615
+ "[P@H]": 527,
616
+ "[Li-]": 528,
617
+ "[7NaH]": 529,
618
+ "[Bi+]": 530,
619
+ "[PtH+2]": 531,
620
+ "[p-]": 532,
621
+ "[Re+5]": 533,
622
+ "[NiH]": 534,
623
+ "[Ni-]": 535,
624
+ "[Xe+]": 536,
625
+ "[Ca+]": 537,
626
+ "[11c]": 538,
627
+ "[Rh+4]": 539,
628
+ "[AcH]": 540,
629
+ "[HeH]": 541,
630
+ "[Sc+2]": 542,
631
+ "[Mn+]": 543,
632
+ "[UH]": 544,
633
+ "[14CH2]": 545,
634
+ "[SiH4+]": 546,
635
+ "[18OH2]": 547,
636
+ "[Ac-]": 548,
637
+ "[Re+4]": 549,
638
+ "[118Sn]": 550,
639
+ "[153Sm]": 551,
640
+ "[P+2]": 552,
641
+ "[9CH]": 553,
642
+ "[9CH3]": 554,
643
+ "[Y-]": 555,
644
+ "[NiH2]": 556,
645
+ "[Si+2]": 557,
646
+ "[Mn+6]": 558,
647
+ "[ZrH2]": 559,
648
+ "[C-2]": 560,
649
+ "[Bi+5]": 561,
650
+ "[24NaH]": 562,
651
+ "[Fr]": 563,
652
+ "[15CH]": 564,
653
+ "[Se+]": 565,
654
+ "[At]": 566,
655
+ "[P-3]": 567,
656
+ "[124I-]": 568,
657
+ "[CuH2-]": 569,
658
+ "[Nb+4]": 570,
659
+ "[Nb+3]": 571,
660
+ "[MgH]": 572,
661
+ "[Ir+4]": 573,
662
+ "[67Ga+3]": 574,
663
+ "[67Ga]": 575,
664
+ "[13N]": 576,
665
+ "[15OH2]": 577,
666
+ "[2NH]": 578,
667
+ "[Ho]": 579,
668
+ "[Cn]": 580
669
+ },
670
+ "merges": []
671
+ }
672
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<unk>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<pad>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "max_len": 512,
53
+ "model_max_length": 512,
54
+ "pad_token": "<pad>",
55
+ "sep_token": "</s>",
56
+ "tokenizer_class": "RobertaTokenizerFast",
57
+ "trim_offsets": true,
58
+ "unk_token": "<unk>"
59
+ }
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<unk>":0,"<s>":1,"</s>":2,"<pad>":3,"<mask>":4,"c":5,"C":6,"(":7,")":8,"O":9,"1":10,"2":11,"=":12,"N":13,".":14,"n":15,"3":16,"F":17,"Cl":18,">>":19,"~":20,"-":21,"4":22,"[C@H]":23,"S":24,"[C@@H]":25,"[O-]":26,"Br":27,"#":28,"/":29,"[nH]":30,"[N+]":31,"s":32,"5":33,"o":34,"P":35,"[Na+]":36,"[Si]":37,"I":38,"[Na]":39,"[Pd]":40,"[K+]":41,"[K]":42,"[P]":43,"B":44,"[C@]":45,"[C@@]":46,"[Cl-]":47,"6":48,"[OH-]":49,"\\":50,"[N-]":51,"[Li]":52,"[H]":53,"[2H]":54,"[NH4+]":55,"[c-]":56,"[P-]":57,"[Cs+]":58,"[Li+]":59,"[Cs]":60,"[NaH]":61,"[H-]":62,"[O+]":63,"[BH4-]":64,"[Cu]":65,"7":66,"[Mg]":67,"[Fe+2]":68,"[n+]":69,"[Sn]":70,"[BH-]":71,"[Pd+2]":72,"[CH]":73,"[I-]":74,"[Br-]":75,"[C-]":76,"[Zn]":77,"[B-]":78,"[F-]":79,"[Al]":80,"[P+]":81,"[BH3-]":82,"[Fe]":83,"[C]":84,"[AlH4]":85,"[Ni]":86,"[SiH]":87,"8":88,"[Cu+2]":89,"[Mn]":90,"[AlH]":91,"[nH+]":92,"[AlH4-]":93,"[O-2]":94,"[Cr]":95,"[Mg+2]":96,"[NH3+]":97,"[S@]":98,"[Pt]":99,"[Al+3]":100,"[S@@]":101,"[S-]":102,"[Ti]":103,"[Zn+2]":104,"[PH]":105,"[NH2+]":106,"[Ru]":107,"[Ag+]":108,"[S+]":109,"[I+3]":110,"[NH+]":111,"[Ca+2]":112,"[Ag]":113,"9":114,"[Os]":115,"[Se]":116,"[SiH2]":117,"[Ca]":118,"[Ti+4]":119,"[Ac]":120,"[Cu+]":121,"[S]":122,"[Rh]":123,"[Cl+3]":124,"[cH-]":125,"[Zn+]":126,"[O]":127,"[Cl+]":128,"[SH]":129,"[H+]":130,"[Pd+]":131,"[se]":132,"[PH+]":133,"[I]":134,"[Pt+2]":135,"[C+]":136,"[Mg+]":137,"[Hg]":138,"[W]":139,"[SnH]":140,"[SiH3]":141,"[Fe+3]":142,"[NH]":143,"[Mo]":144,"[CH2+]":145,"%10":146,"[CH2-]":147,"[CH2]":148,"[n-]":149,"[Ce+4]":150,"[NH-]":151,"[Co]":152,"[I+]":153,"[PH2]":154,"[Pt+4]":155,"[Ce]":156,"[B]":157,"[Sn+2]":158,"[Ba+2]":159,"%11":160,"[Fe-3]":161,"[18F]":162,"[SH-]":163,"[Pb+2]":164,"[Os-2]":165,"[Zr+4]":166,"[N]":167,"[Ir]":168,"[Bi]":169,"[Ni+2]":170,"[P@]":171,"[Co+2]":172,"[s+]":173,"[As]":174,"[P+3]":175,"[Hg+2]":176,"[Yb+3]":177,"[CH-]":178,"[Zr+2]":179,"[Mn+2]":180,"[CH+]":181,"[In]":182,"[KH]":183,"[Ce+3]":184,"[Zr]":185,"[AlH2-]":186,"[OH2+]":187,"[Ti+3]":188,"[Rh+2]":189,"[Sb]":190,"[S-2]":191,"%12":192,"[P@@]":193,"[Si@H]":194,"[Mn+4]":195,"p":196,"[Ba]":197,"[NH2-]":198,"[Ge]":199,"[Pb+4]":200,"[Cr+3]":201,"[Au]":202,"[LiH]":203,"[Sc+3]":204,"[o+]":205,"[Rh-3]":206,"%13":207,"[Br]":208,"[Sb-]":209,"[S@+]":210,"[I+2]":211,"[Ar]":212,"[V]":213,"[Cu-]":214,"[Al-]":215,"[Te]":216,"[13c]":217,"[13C]":218,"[Cl]":219,"[PH4+]":220,"[SiH4]":221,"[te]":222,"[CH3-]":223,"[S@@+]":224,"[Rh+3]":225,"[SH+]":226,"[Bi+3]":227,"[Br+2]":228,"[La]":229,"[La+3]":230,"[Pt-2]":231,"[N@@]":232,"[PH3+]":233,"[N@]":234,"[Si+4]":235,"[Sr+2]":236,"[Al+]":237,"[Pb]":238,"[SeH]":239,"[Si-]":240,"[V+5]":241,"[Y+3]":242,"[Re]":243,"[Ru+]":244,"[Sm]":245,"*":246,"[3H]":247,"[NH2]":248,"[Ag-]":249,"[13CH3]":250,"[OH+]":251,"[Ru+3]":252,"[OH]":253,"[Gd+3]":254,"[13CH2]":255,"[In+3]":256,"[Si@@]":257,"[Si@]":258,"[Ti+2]":259,"[Sn+]":260,"[Cl+2]":261,"[AlH-]":262,"[Pd-2]":263,"[SnH3]":264,"[B+3]":265,"[Cu-2]":266,"[Nd+3]":267,"[Pb+3]":268,"[13cH]":269,"[Fe-4]":270,"[Ga]":271,"[Sn+4]":272,"[Hg+]":273,"[11CH3]":274,"[Hf]":275,"[Pr]":276,"[Y]":277,"[S+2]":278,"[Cd]":279,"[Cr+6]":280,"[Zr+3]":281,"[Rh+]":282,"[CH3]":283,"[N-3]":284,"[Hf+2]":285,"[Th]":286,"[Sb+3]":287,"%14":288,"[Cr+2]":289,"[Ru+2]":290,"[Hf+4]":291,"[14C]":292,"[Ta]":293,"[Tl+]":294,"[B+]":295,"[Os+4]":296,"[PdH2]":297,"[Pd-]":298,"[Cd+2]":299,"[Co+3]":300,"[S+4]":301,"[Nb+5]":302,"[123I]":303,"[c+]":304,"[Rb+]":305,"[V+2]":306,"[CH3+]":307,"[Ag+2]":308,"[cH+]":309,"[Mn+3]":310,"[Se-]":311,"[As-]":312,"[Eu+3]":313,"[SH2]":314,"[Sm+3]":315,"[IH+]":316,"%15":317,"[OH3+]":318,"[PH3]":319,"[IH2+]":320,"[SH2+]":321,"[Ir+3]":322,"[AlH3]":323,"[Sc]":324,"[Yb]":325,"[15NH2]":326,"[Lu]":327,"[sH+]":328,"[Gd]":329,"[18F-]":330,"[SH3+]":331,"[SnH4]":332,"[TeH]":333,"[Si@@H]":334,"[Ga+3]":335,"[CaH2]":336,"[Tl]":337,"[Ta+5]":338,"[GeH]":339,"[Br+]":340,"[Sr]":341,"[Tl+3]":342,"[Sm+2]":343,"[PH5]":344,"%16":345,"[N@@+]":346,"[Au+3]":347,"[C-4]":348,"[Nd]":349,"[Ti+]":350,"[IH]":351,"[N@+]":352,"[125I]":353,"[Eu]":354,"[Sn+3]":355,"[Nb]":356,"[Er+3]":357,"[123I-]":358,"[14c]":359,"%17":360,"[SnH2]":361,"[YH]":362,"[Sb+5]":363,"[Pr+3]":364,"[Ir+]":365,"[N+3]":366,"[AlH2]":367,"[19F]":368,"%18":369,"[Tb]":370,"[14CH]":371,"[Mo+4]":372,"[Si+]":373,"[BH]":374,"[Be]":375,"[Rb]":376,"[pH]":377,"%19":378,"%20":379,"[Xe]":380,"[Ir-]":381,"[Be+2]":382,"[C+4]":383,"[RuH2]":384,"[15NH]":385,"[U+2]":386,"[Au-]":387,"%21":388,"%22":389,"[Au+]":390,"[15n]":391,"[Al+2]":392,"[Tb+3]":393,"[15N]":394,"[V+3]":395,"[W+6]":396,"[14CH3]":397,"[Cr+4]":398,"[ClH+]":399,"b":400,"[Ti+6]":401,"[Nd+]":402,"[Zr+]":403,"[PH2+]":404,"[Fm]":405,"[N@H+]":406,"[RuH]":407,"[Dy+3]":408,"%23":409,"[Hf+3]":410,"[W+4]":411,"[11C]":412,"[13CH]":413,"[Er]":414,"[124I]":415,"[LaH]":416,"[F]":417,"[siH]":418,"[Ga+]":419,"[Cm]":420,"[GeH3]":421,"[IH-]":422,"[U+6]":423,"[SeH+]":424,"[32P]":425,"[SeH-]":426,"[Pt-]":427,"[Ir+2]":428,"[se+]":429,"[U]":430,"[F+]":431,"[BH2]":432,"[As+]":433,"[Cf]":434,"[ClH2+]":435,"[Ni+]":436,"[TeH3]":437,"[SbH2]":438,"[Ag+3]":439,"%24":440,"[18O]":441,"[PH4]":442,"[Os+2]":443,"[Na-]":444,"[Sb+2]":445,"[V+4]":446,"[Ho+3]":447,"[68Ga]":448,"[PH-]":449,"[Bi+2]":450,"[Ce+2]":451,"[Pd+3]":452,"[99Tc]":453,"[13C@@H]":454,"[Fe+6]":455,"[c]":456,"[GeH2]":457,"[10B]":458,"[Cu+3]":459,"[Mo+2]":460,"[Cr+]":461,"[Pd+4]":462,"[Dy]":463,"[AsH]":464,"[Ba+]":465,"[SeH2]":466,"[In+]":467,"[TeH2]":468,"[BrH+]":469,"[14cH]":470,"[W+]":471,"[13C@H]":472,"[AsH2]":473,"[In+2]":474,"[N+2]":475,"[N@@H+]":476,"[SbH]":477,"[60Co]":478,"[AsH4+]":479,"[AsH3]":480,"[18OH]":481,"[Ru-2]":482,"[Na-2]":483,"[CuH2]":484,"[31P]":485,"[Ti+5]":486,"[35S]":487,"[P@@H]":488,"[ArH]":489,"[Co+]":490,"[Zr-2]":491,"[BH2-]":492,"[131I]":493,"[SH5]":494,"[VH]":495,"[B+2]":496,"[Yb+2]":497,"[14C@H]":498,"[211At]":499,"[NH3+2]":500,"[IrH]":501,"[IrH2]":502,"[Rh-]":503,"[Cr-]":504,"[Sb+]":505,"[Ni+3]":506,"[TaH3]":507,"[Tl+2]":508,"[64Cu]":509,"[Tc]":510,"[Cd+]":511,"[1H]":512,"[15nH]":513,"[AlH2+]":514,"[FH+2]":515,"[BiH3]":516,"[Ru-]":517,"[Mo+6]":518,"[AsH+]":519,"[BaH2]":520,"[BaH]":521,"[Fe+4]":522,"[229Th]":523,"[Th+4]":524,"[As+3]":525,"[NH+3]":526,"[P@H]":527,"[Li-]":528,"[7NaH]":529,"[Bi+]":530,"[PtH+2]":531,"[p-]":532,"[Re+5]":533,"[NiH]":534,"[Ni-]":535,"[Xe+]":536,"[Ca+]":537,"[11c]":538,"[Rh+4]":539,"[AcH]":540,"[HeH]":541,"[Sc+2]":542,"[Mn+]":543,"[UH]":544,"[14CH2]":545,"[SiH4+]":546,"[18OH2]":547,"[Ac-]":548,"[Re+4]":549,"[118Sn]":550,"[153Sm]":551,"[P+2]":552,"[9CH]":553,"[9CH3]":554,"[Y-]":555,"[NiH2]":556,"[Si+2]":557,"[Mn+6]":558,"[ZrH2]":559,"[C-2]":560,"[Bi+5]":561,"[24NaH]":562,"[Fr]":563,"[15CH]":564,"[Se+]":565,"[At]":566,"[P-3]":567,"[124I-]":568,"[CuH2-]":569,"[Nb+4]":570,"[Nb+3]":571,"[MgH]":572,"[Ir+4]":573,"[67Ga+3]":574,"[67Ga]":575,"[13N]":576,"[15OH2]":577,"[2NH]":578,"[Ho]":579,"[Cn]":580}