REGEX-4M / tokenizer.json
yzimmermann's picture
Upload tokenizer
d22d49f verified
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "[BOS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "[EOS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "[PAD]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "[UNK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 4,
"content": "[MASK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 5,
"content": "[CLS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 6,
"content": "[SEP]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "Split",
"pattern": {
"Regex": "(\\[[^\\]]+]|Br?|Cl?|N|O|S|P|F|I|b|c|n|o|s|p|\\(|\\)|\\.|=|-|\\+|\\\\|\\/|:|~|@|\\?|>>?|\\*|\\$|\\%[0-9]{2}|[0-9])"
},
"behavior": "Isolated",
"invert": false
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "[BOS]",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "[EOS]",
"type_id": 0
}
}
],
"pair": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {
"[BOS]": {
"id": "[BOS]",
"ids": [
0
],
"tokens": [
"[BOS]"
]
},
"[EOS]": {
"id": "[EOS]",
"ids": [
1
],
"tokens": [
"[EOS]"
]
}
}
},
"decoder": null,
"model": {
"type": "WordLevel",
"vocab": {
"[BOS]": 0,
"[EOS]": 1,
"[PAD]": 2,
"[UNK]": 3,
"[MASK]": 4,
"[CLS]": 5,
"[SEP]": 6,
"C": 7,
"=": 8,
"(": 9,
")": 10,
"O": 11,
"N": 12,
"1": 13,
"2": 14,
"3": 15,
"4": 16,
"S": 17,
"Cl": 18,
"F": 19,
"5": 20,
"[C@@H]": 21,
"[C@H]": 22,
"/": 23,
"[O-]": 24,
"[N+]": 25,
"Br": 26,
"6": 27,
"#": 28,
".": 29,
"\\": 30,
"7": 31,
"[NH+]": 32,
"I": 33,
"[C@@]": 34,
"[C@]": 35,
"P": 36,
"8": 37,
"[Si]": 38,
"9": 39,
"[NH2+]": 40,
"[Cl-]": 41,
"[N-]": 42,
"[Na+]": 43,
"[C-]": 44,
"B": 45,
"[I-]": 46,
"[Br-]": 47,
"[NH3+]": 48,
"[O+]": 49,
"[S-]": 50,
"[NH-]": 51,
"[O-2]": 52,
"[Se]": 53,
"[P+]": 54,
"[OH+]": 55,
"[As]": 56,
"[Sn]": 57,
"[2H]": 58,
"[H+]": 59,
"[K+]": 60,
"[OH2+]": 61,
"[NH2-]": 62,
"[Hg]": 63,
"[CH-]": 64,
"[OH-]": 65,
"[S+]": 66,
"[Pt+2]": 67,
"[Cu+2]": 68,
"[CH]": 69,
"[NH4+]": 70,
"[SH+]": 71,
"[W]": 72,
"[Zn+2]": 73,
"[Ca+2]": 74,
"[Cu]": 75,
"[B-]": 76,
"[Co]": 77,
"[Mg+2]": 78,
"[Mo]": 79,
"[Fe]": 80,
"[CH2-]": 81,
"[Ni+2]": 82,
"[SiH]": 83,
"[Fe+2]": 84,
"[Pt]": 85,
"[Ni]": 86,
"[18F]": 87,
"[Co+2]": 88,
"[F-]": 89,
"[C]": 90,
"[Cr]": 91,
"[Li+]": 92,
"[Fe+3]": 93,
"[Co+3]": 94,
"[Al+3]": 95,
"[Te]": 96,
"[O]": 97,
"[Cr+3]": 98,
"[Ti]": 99,
"[Ge]": 100,
"[11CH3]": 101,
"[V]": 102,
"[Zn]": 103,
"[SH2+]": 104,
"[Mn+2]": 105,
"[Ba+2]": 106,
"[Pd]": 107,
"[Mn]": 108,
"[Rh]": 109,
"[Pt+4]": 110,
"[Ti+4]": 111,
"[Sb]": 112,
"[Pb]": 113,
"[Pd+2]": 114,
"[CH3-]": 115,
"[99Tc]": 116,
"[Ag+]": 117,
"[Ru]": 118,
"[Cu+]": 119,
"[H-]": 120,
"[S-2]": 121,
"[SiH2]": 122,
"[125I]": 123,
"[11C]": 124,
"[P-]": 125,
"[N@+]": 126,
"[Ac]": 127,
"[Hg+2]": 128,
"[N@@+]": 129,
"[Cd+2]": 130,
"[Au]": 131,
"[Sr+2]": 132,
"[Pb+2]": 133,
"[Bi+3]": 134,
"[Re]": 135,
"[I+]": 136,
"[3H]": 137,
"[13C]": 138,
"[Zn+]": 139,
"[Hg+]": 140,
"[Sn+4]": 141,
"[SiH3]": 142,
"[Rh+2]": 143,
"[Gd+3]": 144,
"[Ru+3]": 145,
"[Zr]": 146,
"[Ag]": 147,
"[Au+]": 148,
"[Be+2]": 149,
"[SH-]": 150,
"[Sb+3]": 151,
"[SH3+]": 152,
"[U]": 153,
"[No]": 154,
"[Cs+]": 155,
"[Al]": 156,
"[La+3]": 157,
"[Cd]": 158,
"[Zr+4]": 159,
"[Rh+3]": 160,
"[11CH2]": 161,
"[Ce+3]": 162,
"[Nb]": 163,
"[Ru+2]": 164,
"[CH+]": 165,
"[As+]": 166,
"[Se-2]": 167,
"[Nd+3]": 168,
"[SnH]": 169,
"[Hf]": 170,
"[Os]": 171,
"[Ir]": 172,
"[123I]": 173,
"[131I]": 174,
"[Eu]": 175,
"[SeH]": 176,
"[Ga+3]": 177,
"[AsH]": 178,
"[BH3-]": 179,
"[Sn+2]": 180,
"[Y+3]": 181,
"[1H]": 182,
"[C+]": 183,
"[Rb+]": 184,
"[AlH3]": 185,
"[CH2]": 186,
"[Si+4]": 187,
"[Ta]": 188,
"[Mn+3]": 189,
"[Mo+2]": 190,
"[OH3+]": 191,
"[Tl+]": 192,
"[Pr+3]": 193,
"[In+3]": 194,
"[Co+]": 195,
"[Au+3]": 196,
"[Bi]": 197,
"[Ir+3]": 198,
"[Y]": 199,
"[Eu+3]": 200,
"[Pt+]": 201,
"[Sm+3]": 202,
"[Zr+2]": 203,
"[13CH]": 204,
"[La]": 205,
"[14C]": 206,
"[Ce]": 207,
"[Yb]": 208,
"[Tl]": 209,
"[BH-]": 210,
"[BH2-]": 211,
"[Pr]": 212,
"[Tb]": 213,
"[U+2]": 214,
"[Sm]": 215,
"[Cr+2]": 216,
"[Er]": 217,
"[Nb+5]": 218,
"[Dy+3]": 219,
"[Ga]": 220,
"[Gd]": 221,
"[Lu]": 222,
"[Ho]": 223,
"[11CH]": 224,
"[Tb+3]": 225,
"[Th]": 226,
"[Dy]": 227,
"[Lu+3]": 228,
"[GeH2]": 229,
"[N]": 230,
"[Nd]": 231,
"[P-3]": 232,
"[Ru+4]": 233,
"[Er+3]": 234,
"[Ho+3]": 235,
"[Ru-]": 236,
"[Sc+3]": 237,
"[SnH2]": 238,
"[Tm+3]": 239,
"[Tm]": 240,
"[V+2]": 241,
"[Yb+3]": 242,
"[ClH+]": 243,
"[Ti+2]": 244,
"[PH+]": 245,
"[S@]": 246,
"[Sc]": 247,
"[Se+]": 248,
"[Ta+5]": 249,
"[99Tc+3]": 250,
"[P@]": 251,
"[Th+4]": 252,
"[Tl+3]": 253,
"[Cr+6]": 254,
"[GeH]": 255,
"[PbH]": 256,
"[Pd+]": 257,
"%10": 258,
"[99Tc+4]": 259,
"[AsH2]": 260,
"[Os+2]": 261,
"[ClH2+]": 262,
"[Ni+3]": 263,
"[BH4-]": 264,
"[Ru+]": 265,
"[13NH2]": 266,
"[AlH]": 267,
"[In]": 268,
"[Np]": 269,
"[Ru+5]": 270,
"[S]": 271,
"[Si-]": 272,
"[14CH2]": 273,
"[32P]": 274,
"[Cr+5]": 275,
"[Hf+4]": 276,
"[Pu]": 277,
"[Rh+]": 278,
"[GeH3]": 279,
"[Pt-2]": 280,
"[Sb+]": 281,
"[SbH]": 282,
"[B+]": 283,
"[P@@]": 284,
"[S@@]": 285,
"[PbH2]": 286,
"[Se-]": 287,
"[As-]": 288,
"[Ca]": 289,
"[HH]": 290,
"[Li]": 291,
"[Mo+4]": 292,
"[Ru+8]": 293,
"[Sn+]": 294,
"[14CH3]": 295,
"[17O]": 296,
"[Ce+4]": 297,
"[Cr+4]": 298,
"[Mg]": 299,
"[Na]": 300,
"[Sb-]": 301,
"[Si-2]": 302,
"[Ti+]": 303,
"[TlH]": 304,
"[14CH]": 305,
"[Fe-]": 306,
"[Os+4]": 307,
"[PH2+]": 308,
"[Pd-2]": 309,
"[Ru+6]": 310,
"[Sn-]": 311,
"[W+2]": 312,
"[Zn-2]": 313,
"[Zn-]": 314,
"[111In+3]": 315,
"[Al-]": 316,
"[AlH2]": 317,
"[As+5]": 318,
"[Au-]": 319,
"[Fe+]": 320,
"[Lr]": 321,
"[Mn+]": 322,
"[Mo+3]": 323,
"[Tc]": 324,
"[Ti+3]": 325,
"%11": 326,
"[99Tc+5]": 327,
"[As+3]": 328,
"[B]": 329,
"[Be]": 330,
"[CH2+]": 331,
"[Cm]": 332,
"[Es]": 333,
"[Eu+2]": 334,
"[Hg-2]": 335,
"[IH2+]": 336,
"[K]": 337,
"[NH]": 338,
"[PH2]": 339,
"[SbH2]": 340,
"[SiH4]": 341,
"[SnH3]": 342,
"[Xe]": 343,
"[51Cr]": 344,
"[68Ga+3]": 345,
"[75Se]": 346,
"[76Br]": 347,
"[BiH2]": 348,
"[Hg-]": 349,
"[Rh-]": 350,
"[Ru-2]": 351,
"[Te+]": 352,
"[TeH]": 353,
"%12": 354,
"[203Hg+2]": 355,
"[239Pu]": 356,
"[249Cf]": 357,
"[35S]": 358,
"[37Cl]": 359,
"[74Se]": 360,
"[Am]": 361,
"[Ba]": 362,
"[BiH]": 363,
"[Bk]": 364,
"[Cf]": 365,
"[Cs]": 366,
"[GaH]": 367,
"[He]": 368,
"[InH]": 369,
"[Pm]": 370,
"[Sn+3]": 371,
"[Zr+3]": 372,
"[14C@H]": 373,
"[15N]": 374,
"[203Hg]": 375,
"[211At]": 376,
"[237Np]": 377,
"[241Am]": 378,
"[Al-2]": 379,
"[AlH4-]": 380,
"[AsH3]": 381,
"[Cu-2]": 382,
"[Fe+6]": 383,
"[FeH]": 384,
"[GaH3]": 385,
"[H]": 386,
"[Ni+]": 387,
"[Ni-]": 388,
"[Os+6]": 389,
"[Os+7]": 390,
"[Os+8]": 391,
"[Os+]": 392,
"[PH-]": 393,
"[PH2-]": 394,
"[PbH2+2]": 395,
"[PbH4]": 396,
"[Re-]": 397,
"[Si@]": 398,
"[Sr]": 399,
"[Tc+7]": 400,
"[Te+4]": 401,
"[TlH2]": 402,
"[V+4]": 403,
"[W+]": 404,
"%13": 405,
"[106Ru]": 406,
"[11C@@H]": 407,
"[11C@H]": 408,
"[11CH3-]": 409,
"[122I]": 410,
"[123IH]": 411,
"[125IH]": 412,
"[131I-]": 413,
"[137Cs+]": 414,
"[13CH2]": 415,
"[153Sm+3]": 416,
"[159Dy]": 417,
"[15NH2]": 418,
"[15NH]": 419,
"[165Dy]": 420,
"[186Re]": 421,
"[231Pa]": 422,
"[238Pu]": 423,
"[239Np]": 424,
"[249Bk]": 425,
"[253Cf]": 426,
"[253Es]": 427,
"[33P]": 428,
"[45Ca+2]": 429,
"[55Fe+3]": 430,
"[59Fe+3]": 431,
"[59Fe]": 432,
"[60Co]": 433,
"[65Zn]": 434,
"[67Cu]": 435,
"[77Br]": 436,
"[85Sr+2]": 437,
"[89Sr+2]": 438,
"[90Sr+2]": 439,
"[91Y]": 440,
"[AlH2+]": 441,
"[BiH3]": 442,
"[Cr+]": 443,
"[Fe-3]": 444,
"[FeH2]": 445,
"[GaH2]": 446,
"[Ge-2]": 447,
"[Hf+2]": 448,
"[IH+]": 449,
"[InH2]": 450,
"[Ir+]": 451,
"[Ir-2]": 452,
"[Kr]": 453,
"[Li-]": 454,
"[PH3+]": 455,
"[P]": 456,
"[Pa]": 457,
"[PtH]": 458,
"[Rb]": 459,
"[Rh-2]": 460,
"[Ru-3]": 461,
"[RuH]": 462,
"[SbH3]": 463,
"[Se+4]": 464,
"[SeH2+]": 465,
"[SeH2]": 466,
"[Si@@]": 467,
"[Ta-2]": 468,
"[Tc+3]": 469,
"[Tc+4]": 470,
"[Th+2]": 471,
"[Zr-]": 472,
"[ZrH]": 473,
"[100Pd]": 474,
"[100Rh]": 475,
"[101Mo]": 476,
"[101Pd]": 477,
"[101Rh]": 478,
"[101Tc]": 479,
"[102Ag]": 480,
"[102Rh]": 481,
"[102Ru]": 482,
"[103Ag]": 483,
"[103Ru+2]": 484,
"[103Ru]": 485,
"[104Ag]": 486,
"[104Cd]": 487,
"[104Tc]": 488,
"[105Ag]": 489,
"[105Pd]": 490,
"[105Rh]": 491,
"[105Ru]": 492,
"[106Ag]": 493,
"[106Rh]": 494,
"[107Ag]": 495,
"[107Cd]": 496,
"[107Pd]": 497,
"[107Rh]": 498,
"[108Ag]": 499,
"[108Pd]": 500,
"[109Ag]": 501,
"[109Cd]": 502,
"[109Pd+2]": 503,
"[109Pd]": 504,
"[10BH3]": 505,
"[110Ag+]": 506,
"[110Ag]": 507,
"[110Ru]": 508,
"[111Ag]": 509,
"[111InH3]": 510,
"[112Ag]": 511,
"[113Cd]": 512,
"[115Ag]": 513,
"[115Cd]": 514,
"[117Cd]": 515,
"[117SnH2]": 516,
"[11C-]": 517,
"[11CH4]": 518,
"[120IH]": 519,
"[121IH]": 520,
"[121SnH2]": 521,
"[123I-]": 522,
"[123Xe]": 523,
"[124I-]": 524,
"[124IH]": 525,
"[124I]": 526,
"[125I-]": 527,
"[126IH]": 528,
"[127Te]": 529,
"[127Xe]": 530,
"[128IH]": 531,
"[129I]": 532,
"[130IH]": 533,
"[131IH]": 534,
"[131La]": 535,
"[132IH]": 536,
"[132La]": 537,
"[133Ba+2]": 538,
"[133IH]": 539,
"[133Xe]": 540,
"[134Ce]": 541,
"[134IH]": 542,
"[135Ce]": 543,
"[135IH]": 544,
"[135La]": 545,
"[135Xe]": 546,
"[136Nd]": 547,
"[136Pr]": 548,
"[137Ce]": 549,
"[137La]": 550,
"[137Pr]": 551,
"[138La]": 552,
"[138Nd]": 553,
"[138Pr]": 554,
"[139Ce]": 555,
"[139Nd]": 556,
"[139Pr]": 557,
"[13CH4]": 558,
"[13NH2-]": 559,
"[13NH3]": 560,
"[140La]": 561,
"[141Ce+3]": 562,
"[141Ce]": 563,
"[141La]": 564,
"[141Nd]": 565,
"[141Pm]": 566,
"[141Sm]": 567,
"[142La]": 568,
"[142Pr]": 569,
"[142Sm]": 570,
"[143Ce]": 571,
"[143La]": 572,
"[143Pm]": 573,
"[143Pr]": 574,
"[144Ce]": 575,
"[144Pm]": 576,
"[144Pr]": 577,
"[145Eu]": 578,
"[145Gd]": 579,
"[145Pm]": 580,
"[145Pr]": 581,
"[145Sm]": 582,
"[146Eu]": 583,
"[146Gd]": 584,
"[146Nd]": 585,
"[146Pm]": 586,
"[147Eu]": 587,
"[147Gd]": 588,
"[147Nd]": 589,
"[147Pm]": 590,
"[147Pr]": 591,
"[147Tb]": 592,
"[148Eu]": 593,
"[148Pm]": 594,
"[149Eu]": 595,
"[149Gd]": 596,
"[149Nd]": 597,
"[149Pm]": 598,
"[149Tb]": 599,
"[14CH4]": 600,
"[150Eu]": 601,
"[150Pm]": 602,
"[150Sm]": 603,
"[150Tb]": 604,
"[151Gd]": 605,
"[151Nd]": 606,
"[151Pm]": 607,
"[151Sm]": 608,
"[151Tb]": 609,
"[152Eu]": 610,
"[153Gd]": 611,
"[153Sm]": 612,
"[153Tb]": 613,
"[154Eu]": 614,
"[154Sm]": 615,
"[154Tb]": 616,
"[155Dy]": 617,
"[155Eu]": 618,
"[155Ho]": 619,
"[155Sm]": 620,
"[155Tb]": 621,
"[156Eu]": 622,
"[156Sm]": 623,
"[156Tb]": 624,
"[157Eu]": 625,
"[157Ho]": 626,
"[157Tb]": 627,
"[158Eu]": 628,
"[158Gd]": 629,
"[158Tb]": 630,
"[159Gd]": 631,
"[159Ho]": 632,
"[15CH4]": 633,
"[15NH3]": 634,
"[15OH]": 635,
"[160Gd]": 636,
"[160Tb]": 637,
"[161Er]": 638,
"[161Gd]": 639,
"[161Ho]": 640,
"[161Tb]": 641,
"[162Dy]": 642,
"[162Ho]": 643,
"[162Tm]": 644,
"[162Yb]": 645,
"[164Ho]": 646,
"[165Er]": 647,
"[166Dy]": 648,
"[166Er]": 649,
"[166Ho]": 650,
"[166Tm]": 651,
"[166Yb]": 652,
"[167Ho]": 653,
"[167Tm]": 654,
"[167Yb]": 655,
"[168Er]": 656,
"[169Er]": 657,
"[169Lu]": 658,
"[169Yb]": 659,
"[170Er]": 660,
"[170Hf]": 661,
"[170Lu]": 662,
"[170Tm]": 663,
"[171Er]": 664,
"[171Lu]": 665,
"[171Tm]": 666,
"[172Er]": 667,
"[172Hf]": 668,
"[172Lu]": 669,
"[172Ta]": 670,
"[172Tm]": 671,
"[173Hf]": 672,
"[173Lu]": 673,
"[173Ta]": 674,
"[173Tm]": 675,
"[174Lu]": 676,
"[174Ta]": 677,
"[174Yb]": 678,
"[175Hf]": 679,
"[175Ta]": 680,
"[175Tm]": 681,
"[175Yb]": 682,
"[176Lu]": 683,
"[176Ta]": 684,
"[176W]": 685,
"[176Yb]": 686,
"[177Hf]": 687,
"[177Lu]": 688,
"[177Re]": 689,
"[177Ta]": 690,
"[177W]": 691,
"[177Yb]": 692,
"[178Hf]": 693,
"[178Lu]": 694,
"[178Re]": 695,
"[178Ta]": 696,
"[178W]": 697,
"[178Yb]": 698,
"[179Hf]": 699,
"[179Lu]": 700,
"[179Ta]": 701,
"[179W]": 702,
"[17NH3]": 703,
"[180Hf]": 704,
"[180Os]": 705,
"[180Ta]": 706,
"[181Hf]": 707,
"[181Os]": 708,
"[181Re]": 709,
"[181W]": 710,
"[182Hf]": 711,
"[182Ir]": 712,
"[182Os]": 713,
"[182Re]": 714,
"[182Ta]": 715,
"[183Hf]": 716,
"[184Hf]": 717,
"[184Ir]": 718,
"[184Re]": 719,
"[184Ta]": 720,
"[185Ir]": 721,
"[185Os]": 722,
"[185Ta]": 723,
"[185W]": 724,
"[186Ir]": 725,
"[186Pt]": 726,
"[186Ta]": 727,
"[187Ir]": 728,
"[187Re]": 729,
"[187W]": 730,
"[188Ir]": 731,
"[188Pt]": 732,
"[188Re]": 733,
"[188W]": 734,
"[189Ir]": 735,
"[189Os]": 736,
"[189Pt]": 737,
"[189Re]": 738,
"[18FH]": 739,
"[18OH2]": 740,
"[18O]": 741,
"[190Ir]": 742,
"[191Os]": 743,
"[191Pt]": 744,
"[192Ir]": 745,
"[193Au]": 746,
"[193Hg]": 747,
"[193Os]": 748,
"[193Pt]": 749,
"[194Au]": 750,
"[194Hg]": 751,
"[194Ir]": 752,
"[194Os]": 753,
"[195Au]": 754,
"[195Hg]": 755,
"[195Ir]": 756,
"[195Pt]": 757,
"[197Hg]": 758,
"[197Pt]": 759,
"[198Au]": 760,
"[199Au]": 761,
"[199Hg]": 762,
"[199Pt]": 763,
"[1H-]": 764,
"[200Au]": 765,
"[200Pt]": 766,
"[201Au]": 767,
"[201Tl+]": 768,
"[210BiH3]": 769,
"[210PoH2]": 770,
"[212PbH2]": 771,
"[218Rn]": 772,
"[219Rn]": 773,
"[220Rn]": 774,
"[222Rn]": 775,
"[224Ac]": 776,
"[224Rn]": 777,
"[225Ac]": 778,
"[226Ac]": 779,
"[226Rn]": 780,
"[226Th]": 781,
"[227Ac]": 782,
"[227Pa]": 783,
"[227Th]": 784,
"[228Ac]": 785,
"[228Pa]": 786,
"[228Rn]": 787,
"[228Th]": 788,
"[229Th]": 789,
"[230Pa]": 790,
"[230Pu]": 791,
"[230Th]": 792,
"[230U]": 793,
"[231Th]": 794,
"[231U]": 795,
"[232Np]": 796,
"[232Pa]": 797,
"[232U]": 798,
"[233Np]": 799,
"[233Pa]": 800,
"[233U]": 801,
"[234Np]": 802,
"[234Pa]": 803,
"[234Pu]": 804,
"[234Th]": 805,
"[234U]": 806,
"[235Np]": 807,
"[235Pu]": 808,
"[235U]": 809,
"[236Np]": 810,
"[236Pu]": 811,
"[236U]": 812,
"[237Am]": 813,
"[237Pu]": 814,
"[237U]": 815,
"[238Am]": 816,
"[238Cm]": 817,
"[238Np]": 818,
"[238Th]": 819,
"[239Am]": 820,
"[239U]": 821,
"[240Am]": 822,
"[240Cm]": 823,
"[240Np]": 824,
"[240Pu]": 825,
"[240U]": 826,
"[241Cm]": 827,
"[241Pu]": 828,
"[242Am]": 829,
"[242Cm]": 830,
"[242Pu]": 831,
"[243Am]": 832,
"[243Cm]": 833,
"[243Pu]": 834,
"[244Am]": 835,
"[244Cf]": 836,
"[244Cm]": 837,
"[244Pu]": 838,
"[245Am]": 839,
"[245Bk]": 840,
"[245Cm]": 841,
"[245Pu]": 842,
"[246Am]": 843,
"[246Bk]": 844,
"[246Cf]": 845,
"[246Cm]": 846,
"[246Pu]": 847,
"[247Bk]": 848,
"[247Cm]": 849,
"[248Am]": 850,
"[248Cf]": 851,
"[248Cm]": 852,
"[249Cm]": 853,
"[250Bk]": 854,
"[250Cf]": 855,
"[250Cm]": 856,
"[250Es]": 857,
"[251Cf]": 858,
"[251Es]": 859,
"[252Cf]": 860,
"[252Fm]": 861,
"[253Fm]": 862,
"[254Cf]": 863,
"[254Es]": 864,
"[254Fm]": 865,
"[255Fm]": 866,
"[257Fm]": 867,
"[257Md]": 868,
"[258Md]": 869,
"[2HH]": 870,
"[32PH3]": 871,
"[32SH2]": 872,
"[33PH3]": 873,
"[34SH2]": 874,
"[35S-2]": 875,
"[35SH2]": 876,
"[36ClH]": 877,
"[36SH2]": 878,
"[38ClH]": 879,
"[39ClH]": 880,
"[3HH]": 881,
"[40PH3]": 882,
"[41Ar]": 883,
"[43Sc]": 884,
"[44Sc]": 885,
"[44Ti]": 886,
"[45Ti]": 887,
"[46Sc]": 888,
"[47Sc]": 889,
"[47V]": 890,
"[48Cr]": 891,
"[48Sc]": 892,
"[48V]": 893,
"[49Cr]": 894,
"[49Sc]": 895,
"[49V]": 896,
"[51Cr+3]": 897,
"[51Cr+6]": 898,
"[51Mn]": 899,
"[52Mn]": 900,
"[53Mn]": 901,
"[54Mn]": 902,
"[55Co]": 903,
"[55Fe]": 904,
"[56Co]": 905,
"[56Mn]": 906,
"[56Ni]": 907,
"[57Co+2]": 908,
"[57Co]": 909,
"[57Fe]": 910,
"[57Ni]": 911,
"[58Co]": 912,
"[58Ni]": 913,
"[59Fe+2]": 914,
"[59Ni]": 915,
"[60Co+2]": 916,
"[60Co+3]": 917,
"[60Cu]": 918,
"[60Fe]": 919,
"[61Co]": 920,
"[61Cu]": 921,
"[61Ni]": 922,
"[62Co]": 923,
"[62Zn]": 924,
"[63Ni]": 925,
"[63Zn]": 926,
"[64Cu]": 927,
"[65Ni]": 928,
"[65Zn+2]": 929,
"[66Ni]": 930,
"[67Ga+3]": 931,
"[67GaH3]": 932,
"[68GaH3]": 933,
"[69Zn]": 934,
"[71Zn]": 935,
"[72Br-]": 936,
"[72BrH]": 937,
"[72Zn]": 938,
"[74BrH]": 939,
"[75BrH]": 940,
"[75Br]": 941,
"[76BrH]": 942,
"[77BrH]": 943,
"[79Kr]": 944,
"[80BrH]": 945,
"[80Br]": 946,
"[81Kr]": 947,
"[82BrH]": 948,
"[82Rb+]": 949,
"[83BrH]": 950,
"[84BrH]": 951,
"[85Kr]": 952,
"[86Y]": 953,
"[86Zr]": 954,
"[87Y]": 955,
"[88Nb]": 956,
"[88Y]": 957,
"[88Zr]": 958,
"[89Kr]": 959,
"[89Nb]": 960,
"[89Zr]": 961,
"[90Mo]": 962,
"[90Nb]": 963,
"[90Y+3]": 964,
"[90Y]": 965,
"[92Y]": 966,
"[93Mo]": 967,
"[93Tc]": 968,
"[93Y]": 969,
"[93Zr]": 970,
"[94Nb]": 971,
"[94Ru]": 972,
"[94Tc]": 973,
"[94Y]": 974,
"[95Nb]": 975,
"[95Y]": 976,
"[95Zr]": 977,
"[96Nb]": 978,
"[96Tc]": 979,
"[97Nb]": 980,
"[97Ru]": 981,
"[97Tc]": 982,
"[97Zr]": 983,
"[98Nb]": 984,
"[98Tc]": 985,
"[99Mo]": 986,
"[99Rh]": 987,
"[99Ru]": 988,
"[99Tc+]": 989,
"[Ag-]": 990,
"[AgH]": 991,
"[Al-3]": 992,
"[AlH+2]": 993,
"[Ar]": 994,
"[AtH]": 995,
"[At]": 996,
"[B@-]": 997,
"[BH2]": 998,
"[Bi+2]": 999,
"[Br]": 1000,
"[CH3+]": 1001,
"[CH3]": 1002,
"[Cd-2]": 1003,
"[Cl+3]": 1004,
"[CoH2]": 1005,
"[Cu-]": 1006,
"[CuH]": 1007,
"[Fm]": 1008,
"[Ga-]": 1009,
"[Gd+2]": 1010,
"[GeH4]": 1011,
"[I]": 1012,
"[InH3]": 1013,
"[Ir+2]": 1014,
"[IrH+2]": 1015,
"[Md]": 1016,
"[Mn-2]": 1017,
"[MoH2]": 1018,
"[NH2]": 1019,
"[Nb+2]": 1020,
"[Ne]": 1021,
"[Ni-2]": 1022,
"[NiH]": 1023,
"[OH]": 1024,
"[Os+5]": 1025,
"[OsH]": 1026,
"[PH4+]": 1027,
"[PoH2]": 1028,
"[Re-2]": 1029,
"[ReH]": 1030,
"[Rh-3]": 1031,
"[RhH+2]": 1032,
"[RhH]": 1033,
"[Rn]": 1034,
"[Se+6]": 1035,
"[Se@@H]": 1036,
"[Si+]": 1037,
"[Si@@H]": 1038,
"[SiH-]": 1039,
"[SiH3-]": 1040,
"[SnH4]": 1041,
"[SrH2]": 1042,
"[Ta+2]": 1043,
"[TaH2]": 1044,
"[Tc+6]": 1045,
"[Te-]": 1046,
"[TeH2]": 1047,
"[TlH3]": 1048,
"[WH2]": 1049,
"[Yb+2]": 1050,
"[ZrH2]": 1051
},
"unk_token": "[UNK]"
}
}