ApeTokenizer-SELFIES / vocab.json
jsture's picture
Add APE SELFIES tokenizer with max length 256
891e224 verified
Raw
History Blame Contribute Delete
13 kB
{
"</s>": 2,
"<mask>": 4,
"<pad>": 1,
"<s>": 0,
"<unk>": 3,
"[#11C]": 256,
"[#14C]": 247,
"[#Branch1]": 22,
"[#Branch1][=C]": 479,
"[#Branch1][=O]": 542,
"[#Branch1][C]": 400,
"[#Branch1][N]": 453,
"[#Branch1][O]": 491,
"[#Branch1][S]": 528,
"[#Branch2]": 15,
"[#Branch2][=C]": 469,
"[#Branch2][=N]": 561,
"[#Branch2][=O]": 531,
"[#Branch2][C]": 380,
"[#Branch2][N]": 438,
"[#Branch2][O]": 461,
"[#Branch2][S]": 529,
"[#C-1]": 141,
"[#CH0]": 248,
"[#C]": 23,
"[#C][=C]": 496,
"[#C][=N]": 569,
"[#C][=O]": 515,
"[#C][C]": 407,
"[#C][N]": 465,
"[#C][O]": 538,
"[#C][S]": 534,
"[#N+1]": 123,
"[#N]": 19,
"[#N][=C]": 435,
"[#N][C]": 475,
"[#O+1]": 589,
"[#S]": 262,
"[-/Ring1]": 92,
"[-/Ring2]": 90,
"[-/Ring3]": 590,
"[-\\Ring1]": 167,
"[-\\Ring2]": 120,
"[-\\Ring3]": 591,
"[/123I]": 245,
"[/125I]": 117,
"[/131I]": 210,
"[/13CH1]": 272,
"[/13C]": 197,
"[/14CH1]": 324,
"[/14C]": 281,
"[/As]": 259,
"[/B]": 161,
"[/Br]": 62,
"[/C-1]": 229,
"[/C@@H1]": 45,
"[/C@@]": 105,
"[/C@H1]": 87,
"[/C@]": 76,
"[/C]": 20,
"[/C][=Branch1]": 428,
"[/C][=Branch2]": 450,
"[/C][=C]": 364,
"[/C][=N]": 454,
"[/C][Branch1]": 540,
"[/C][C]": 564,
"[/Cl]": 101,
"[/F]": 160,
"[/I]": 94,
"[/N+1]": 68,
"[/N-1]": 142,
"[/NH1]": 114,
"[/N]": 48,
"[/N][=C]": 418,
"[/N][=N]": 580,
"[/N][C]": 499,
"[/O-1]": 128,
"[/O]": 53,
"[/P+1]": 181,
"[/P@@]": 231,
"[/P]": 102,
"[/S+1]": 67,
"[/S-1]": 258,
"[/SH0]": 303,
"[/S]": 71,
"[/Se]": 149,
"[/Si]": 125,
"[10B]": 283,
"[11C@@H1]": 304,
"[11CH2]": 249,
"[11CH3]": 74,
"[11C]": 137,
"[123I-1]": 312,
"[123I]": 69,
"[123Te]": 186,
"[124I-1]": 325,
"[124I]": 133,
"[125I-1]": 171,
"[125I]": 70,
"[127I]": 301,
"[127Xe]": 311,
"[129Xe]": 292,
"[131Cs]": 275,
"[131I-1]": 329,
"[131I]": 86,
"[133Xe]": 322,
"[13CH1]": 198,
"[13CH3]": 277,
"[13C]": 166,
"[14C@@H1]": 318,
"[14C@@]": 302,
"[14C@H1]": 306,
"[14CH1]": 185,
"[14CH2]": 175,
"[14CH3]": 177,
"[14C]": 143,
"[15NH1]": 200,
"[15N]": 134,
"[17F]": 218,
"[18F-1]": 294,
"[18F]": 73,
"[18OH1]": 252,
"[19F]": 144,
"[211At]": 286,
"[223Ra]": 193,
"[22Na+1]": 191,
"[2H]": 88,
"[32P]": 307,
"[35S]": 182,
"[3H]": 103,
"[42K+1]": 188,
"[45Ca+2]": 178,
"[47Ca+2]": 201,
"[68Ga+3]": 273,
"[73Se]": 242,
"[75Se]": 327,
"[76Br]": 152,
"[81Kr]": 326,
"[82Rb+1]": 314,
"[82Rb]": 280,
"[85Sr+2]": 180,
"[89Sr+2]": 319,
"[=11C]": 132,
"[=13CH1]": 196,
"[=13C]": 199,
"[=14CH1]": 156,
"[=14C]": 194,
"[=18O]": 317,
"[=32PH1]": 257,
"[=32P]": 244,
"[=Al]": 295,
"[=As]": 145,
"[=B-1]": 159,
"[=B]": 176,
"[=Branch1]": 13,
"[=Branch1][=C]": 451,
"[=Branch1][=N]": 563,
"[=Branch1][=O]": 546,
"[=Branch1][C]": 335,
"[=Branch1][N+1]": 448,
"[=Branch1][N]": 508,
"[=Branch1][O]": 518,
"[=Branch2]": 14,
"[=Branch2][=C]": 472,
"[=Branch2][=N]": 584,
"[=Branch2][=O]": 549,
"[=Branch2][=Ring1]": 556,
"[=Branch2][C]": 383,
"[=Branch2][N]": 424,
"[=Branch2][O]": 507,
"[=Branch2][S]": 509,
"[=Branch3]": 592,
"[=C+1]": 267,
"[=CH0]": 593,
"[=C]": 7,
"[=C][=C]": 492,
"[=C][=O]": 516,
"[=C][Branch1]": 467,
"[=C][C]": 388,
"[=C][N]": 437,
"[=C][O]": 495,
"[=C][Ring1]": 482,
"[=C][S]": 456,
"[=Mg]": 310,
"[=N+1]": 32,
"[=N-1]": 63,
"[=NH1+1]": 232,
"[=NH2+1]": 243,
"[=N]": 29,
"[=N][=C]": 473,
"[=N][=N]": 579,
"[=N][=O]": 517,
"[=N][C]": 362,
"[=N][NH1]": 443,
"[=N][N]": 382,
"[=N][O]": 427,
"[=N][Ring1]": 513,
"[=N][S]": 501,
"[=O+1]": 116,
"[=OH0]": 296,
"[=OH1+1]": 594,
"[=O]": 18,
"[=O][/C]": 572,
"[=O][=C]": 411,
"[=O][=N]": 583,
"[=O][=O]": 425,
"[=O][C@@H1]": 414,
"[=O][C@@]": 544,
"[=O][C@H1]": 431,
"[=O][C@]": 514,
"[=O][C]": 361,
"[=O][NH1]": 434,
"[=O][N]": 345,
"[=O][O-1]": 391,
"[=O][O]": 370,
"[=O][S]": 571,
"[=P@@]": 107,
"[=P@]": 129,
"[=PH1]": 147,
"[=PH2]": 204,
"[=P]": 57,
"[=Ring1]": 34,
"[=Ring1][#Branch1]": 570,
"[=Ring1][#Branch2]": 576,
"[=Ring1][#C]": 562,
"[=Ring1][=Branch1]": 539,
"[=Ring1][=Branch2]": 481,
"[=Ring1][=C]": 582,
"[=Ring1][=N]": 545,
"[=Ring1][Branch1]": 442,
"[=Ring1][Branch2]": 568,
"[=Ring1][N]": 557,
"[=Ring1][O]": 526,
"[=Ring1][P]": 581,
"[=Ring1][S]": 565,
"[=Ring2]": 41,
"[=Ring2][Ring1]": 506,
"[=S+1]": 98,
"[=S-1]": 278,
"[=S@@]": 50,
"[=S@]": 164,
"[=SH0]": 269,
"[=SH1]": 150,
"[=S]": 26,
"[=S][N]": 455,
"[=Se+1]": 174,
"[=Se]": 162,
"[=Si]": 173,
"[=Te+1]": 179,
"[=Te]": 253,
"[Ag+1]": 190,
"[Ag-4]": 328,
"[Ag]": 146,
"[Al+3]": 223,
"[Al]": 225,
"[Ar]": 266,
"[As+1]": 189,
"[As-1]": 298,
"[AsH1]": 282,
"[AsH3]": 316,
"[As]": 84,
"[At]": 290,
"[Au-1]": 595,
"[B-1]": 100,
"[B@-1]": 206,
"[B@@-1]": 208,
"[BH0]": 165,
"[BH1-1]": 251,
"[BH2-1]": 202,
"[BH3-1]": 131,
"[B]": 65,
"[Ba+2]": 157,
"[Ba]": 291,
"[Be+2]": 246,
"[Bi+3]": 169,
"[Bi]": 155,
"[Br+2]": 254,
"[Br-1]": 52,
"[BrH0]": 596,
"[Br]": 21,
"[Br][=C]": 432,
"[Br][C]": 558,
"[Branch1]": 11,
"[Branch1][#Branch1]": 410,
"[Branch1][#Branch2]": 392,
"[Branch1][#C]": 399,
"[Branch1][=Branch1]": 401,
"[Branch1][=Branch2]": 358,
"[Branch1][=C]": 379,
"[Branch1][=N]": 405,
"[Branch1][=O]": 532,
"[Branch1][Branch1]": 476,
"[Branch1][Branch2]": 394,
"[Branch1][C]": 336,
"[Branch1][N]": 378,
"[Branch1][O]": 398,
"[Branch1][P]": 403,
"[Branch1][Ring1]": 396,
"[Branch1][Ring2]": 429,
"[Branch1][S]": 402,
"[Branch2]": 8,
"[Branch2][#Branch1]": 551,
"[Branch2][=Branch1]": 446,
"[Branch2][=C]": 464,
"[Branch2][=N]": 560,
"[Branch2][=O]": 522,
"[Branch2][Branch1]": 384,
"[Branch2][C]": 409,
"[Branch2][N]": 440,
"[Branch2][O]": 478,
"[Branch2][Ring1]": 340,
"[Branch2][Ring2]": 350,
"[Branch2][S]": 535,
"[Branch3]": 597,
"[C+1]": 106,
"[C-1]": 119,
"[C@@H1]": 27,
"[C@@H1][Branch1]": 371,
"[C@@H1][C@@H1]": 547,
"[C@@H1][C@H1]": 586,
"[C@@H1][C]": 447,
"[C@@H1][O]": 493,
"[C@@H1][Ring1]": 524,
"[C@@]": 28,
"[C@@][Branch1]": 413,
"[C@H1]": 33,
"[C@H1][Branch1]": 366,
"[C@H1][Branch2]": 573,
"[C@H1][C@@H1]": 505,
"[C@H1][C@H1]": 575,
"[C@H1][C]": 445,
"[C@H1][O]": 530,
"[C@H1][Ring1]": 470,
"[C@]": 35,
"[C@][Branch1]": 412,
"[CH0]": 227,
"[CH1-1]": 138,
"[CH1]": 323,
"[CH2-1]": 598,
"[CH2]": 224,
"[CH3]": 226,
"[C]": 5,
"[C][#C]": 500,
"[C][#N]": 536,
"[C][=Branch1]": 377,
"[C][=Branch2]": 488,
"[C][=C]": 333,
"[C][=N+1]": 543,
"[C][=N]": 346,
"[C][=O]": 511,
"[C][=Ring1]": 395,
"[C][=Ring2]": 471,
"[C][Branch1]": 342,
"[C][Branch2]": 423,
"[C][C@@H1]": 386,
"[C][C@@]": 480,
"[C][C@H1]": 385,
"[C][C@]": 462,
"[C][C]": 334,
"[C][Cl]": 574,
"[C][F]": 578,
"[C][NH1]": 449,
"[C][N]": 352,
"[C][O]": 348,
"[C][Ring1]": 351,
"[C][Ring2]": 588,
"[C][S]": 397,
"[Ca+2]": 122,
"[CaH2]": 288,
"[Ca]": 234,
"[Cl+1]": 139,
"[Cl+2]": 240,
"[Cl+3]": 61,
"[Cl-1]": 39,
"[ClH0]": 126,
"[ClH1+1]": 599,
"[ClH2+1]": 600,
"[Cl]": 24,
"[Cl][=C]": 374,
"[Cl][=N]": 494,
"[Cl][C]": 416,
"[Cl][Cl]": 484,
"[Cl][N]": 512,
"[Cl][O]": 587,
"[Cl][S]": 555,
"[Co-2]": 601,
"[Co-4]": 602,
"[Cr]": 603,
"[Cs+1]": 85,
"[Cs]": 284,
"[Cu-2]": 604,
"[Cu-3]": 605,
"[Cu-5]": 606,
"[Cu]": 607,
"[F-1]": 111,
"[F]": 16,
"[F][=C]": 376,
"[F][=N]": 537,
"[F][C]": 404,
"[F][F]": 360,
"[F][N]": 585,
"[F][O]": 577,
"[Fe+2]": 608,
"[Fe+3]": 609,
"[Fe-2]": 610,
"[Fe-3]": 611,
"[Gd+3]": 612,
"[Ge]": 613,
"[H+1]": 151,
"[H-1]": 285,
"[H]": 614,
"[He]": 115,
"[Hg]": 615,
"[I+1]": 153,
"[I+2]": 308,
"[I+3]": 309,
"[I-1]": 66,
"[IH0]": 183,
"[I]": 42,
"[Ir-3]": 616,
"[K+1]": 83,
"[KH1]": 228,
"[K]": 313,
"[Kr]": 315,
"[Li+1]": 110,
"[LiH1]": 233,
"[Li]": 276,
"[Mg+1]": 289,
"[Mg+2]": 75,
"[MgH2]": 236,
"[Mg]": 235,
"[Mn+1]": 617,
"[Mn+2]": 618,
"[Mo]": 619,
"[N+1]": 30,
"[N+1][=C]": 510,
"[N+1][Branch1]": 497,
"[N-1]": 37,
"[N@+1]": 97,
"[N@@+1]": 109,
"[N@@]": 140,
"[N@H1+1]": 297,
"[N@]": 91,
"[NH0]": 238,
"[NH1+1]": 216,
"[NH1-1]": 124,
"[NH1]": 38,
"[NH1][C]": 406,
"[NH1][Ring1]": 566,
"[NH2+1]": 215,
"[NH2-1]": 620,
"[NH2]": 621,
"[NH3+1]": 293,
"[NH4+1]": 260,
"[N]": 10,
"[N][#C]": 422,
"[N][=C]": 343,
"[N][=N]": 389,
"[N][=O]": 417,
"[N][=Ring1]": 420,
"[N][=Ring2]": 457,
"[N][Branch1]": 347,
"[N][Branch2]": 498,
"[N][C@@H1]": 486,
"[N][C@H1]": 483,
"[N][C]": 339,
"[N][N]": 430,
"[N][O]": 468,
"[N][Ring1]": 415,
"[N][S]": 408,
"[Na+1]": 40,
"[NaH1]": 221,
"[Na]": 268,
"[Ni-2]": 622,
"[Ni-4]": 623,
"[O+1]": 136,
"[O-1]": 31,
"[O-2]": 270,
"[OH0]": 96,
"[OH1+1]": 220,
"[OH1-1]": 154,
"[OH1]": 212,
"[OH2+1]": 624,
"[OH3+1]": 274,
"[O]": 6,
"[O][=C]": 349,
"[O][=N+1]": 503,
"[O][=N]": 474,
"[O][=O]": 521,
"[O][=S]": 460,
"[O][Branch1]": 559,
"[O][C@@H1]": 390,
"[O][C@@]": 553,
"[O][C@H1]": 387,
"[O][C@]": 519,
"[O][C]": 341,
"[O][N]": 441,
"[O][O]": 426,
"[O][P]": 489,
"[O][Ring1]": 458,
"[O][S]": 487,
"[P+1]": 112,
"[P-1]": 135,
"[P@+1]": 163,
"[P@@+1]": 237,
"[P@@]": 78,
"[P@]": 72,
"[PH1]": 127,
"[PH2+1]": 305,
"[P]": 25,
"[P][=C]": 504,
"[P][=O]": 552,
"[P][C]": 419,
"[P][N]": 477,
"[P][O]": 548,
"[P][S]": 533,
"[Pd-2]": 625,
"[Pt-2]": 626,
"[Pt]": 627,
"[Ra]": 187,
"[Rb+1]": 207,
"[Rb]": 321,
"[Rh+2]": 628,
"[Ring1]": 9,
"[Ring1][#Branch1]": 344,
"[Ring1][#Branch2]": 353,
"[Ring1][#C]": 369,
"[Ring1][=Branch1]": 338,
"[Ring1][=Branch2]": 356,
"[Ring1][=C]": 363,
"[Ring1][=N]": 367,
"[Ring1][=O]": 550,
"[Ring1][Branch1]": 355,
"[Ring1][Branch2]": 357,
"[Ring1][C]": 373,
"[Ring1][N]": 368,
"[Ring1][O]": 354,
"[Ring1][P]": 372,
"[Ring1][Ring1]": 421,
"[Ring1][Ring2]": 439,
"[Ring1][S]": 365,
"[Ring2]": 12,
"[Ring2][=C]": 381,
"[Ring2][=N]": 459,
"[Ring2][=O]": 525,
"[Ring2][Branch1]": 520,
"[Ring2][C]": 393,
"[Ring2][N]": 433,
"[Ring2][O]": 466,
"[Ring2][Ring1]": 337,
"[Ring2][Ring2]": 359,
"[Ring2][S]": 502,
"[Ring3]": 629,
"[S+1]": 44,
"[S-1]": 60,
"[S-2]": 172,
"[S@+1]": 56,
"[S@@+1]": 95,
"[S@@]": 51,
"[S@]": 184,
"[SH0]": 170,
"[SH1+1]": 263,
"[SH1-1]": 205,
"[SH1]": 264,
"[SH2]": 299,
"[S]": 17,
"[S][=C]": 490,
"[S][=N]": 523,
"[S][=O]": 554,
"[S][Branch1]": 444,
"[S][C]": 375,
"[S][N]": 452,
"[S][O]": 527,
"[S][Ring1]": 485,
"[S][S]": 463,
"[Sb]": 211,
"[Se+1]": 230,
"[SeH1]": 130,
"[SeH2]": 330,
"[Se]": 36,
"[Si-1]": 331,
"[Si@]": 287,
"[SiH1-1]": 192,
"[SiH1]": 104,
"[SiH2]": 300,
"[SiH3-1]": 219,
"[SiH4]": 271,
"[Si]": 49,
"[Sn]": 630,
"[Sr+2]": 158,
"[Sr]": 332,
"[TeH1]": 279,
"[TeH2]": 239,
"[Te]": 81,
"[Xe]": 320,
"[Yb]": 209,
"[Zn+1]": 213,
"[Zn+2]": 148,
"[Zn-2]": 261,
"[Zn]": 82,
"[\\11CH3]": 203,
"[\\123I]": 214,
"[\\125I]": 79,
"[\\3H]": 250,
"[\\B]": 217,
"[\\Br]": 89,
"[\\C-1]": 265,
"[\\C@@H1]": 46,
"[\\C@@]": 80,
"[\\C@H1]": 77,
"[\\C@]": 99,
"[\\CH1-1]": 241,
"[\\C]": 43,
"[\\C][=C]": 436,
"[\\C][C]": 567,
"[\\Cl]": 58,
"[\\F]": 118,
"[\\I]": 59,
"[\\N+1]": 113,
"[\\N-1]": 222,
"[\\NH1]": 108,
"[\\N]": 55,
"[\\N][C]": 541,
"[\\O-1]": 64,
"[\\O]": 47,
"[\\P]": 93,
"[\\S+1]": 121,
"[\\S-1]": 255,
"[\\S]": 54,
"[\\Se]": 168,
"[\\Si]": 195
}