| { |
| "version": "1.0", |
| "truncation": { |
| "direction": "Right", |
| "max_length": 128, |
| "strategy": "LongestFirst", |
| "stride": 0 |
| }, |
| "padding": { |
| "strategy": "BatchLongest", |
| "direction": "Right", |
| "pad_to_multiple_of": null, |
| "pad_id": 1, |
| "pad_type_id": 0, |
| "pad_token": "<pad>" |
| }, |
| "added_tokens": [ |
| { |
| "id": 0, |
| "content": "<s>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": true, |
| "special": true |
| }, |
| { |
| "id": 1, |
| "content": "<pad>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": true, |
| "special": true |
| }, |
| { |
| "id": 2, |
| "content": "</s>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": true, |
| "special": true |
| }, |
| { |
| "id": 3, |
| "content": "<unk>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": true, |
| "special": true |
| }, |
| { |
| "id": 4, |
| "content": "<mask>", |
| "single_word": false, |
| "lstrip": true, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| } |
| ], |
| "normalizer": null, |
| "pre_tokenizer": { |
| "type": "ByteLevel", |
| "add_prefix_space": false, |
| "trim_offsets": true, |
| "use_regex": true |
| }, |
| "post_processor": { |
| "type": "RobertaProcessing", |
| "sep": [ |
| "</s>", |
| 2 |
| ], |
| "cls": [ |
| "<s>", |
| 0 |
| ], |
| "trim_offsets": true, |
| "add_prefix_space": false |
| }, |
| "decoder": { |
| "type": "ByteLevel", |
| "add_prefix_space": true, |
| "trim_offsets": true, |
| "use_regex": true |
| }, |
| "model": { |
| "type": "BPE", |
| "dropout": null, |
| "unk_token": null, |
| "continuing_subword_prefix": "", |
| "end_of_word_suffix": "", |
| "fuse_unk": false, |
| "byte_fallback": false, |
| "ignore_merges": false, |
| "vocab": { |
| "<s>": 0, |
| "<pad>": 1, |
| "</s>": 2, |
| "<unk>": 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 |
| }, |
| "merges": [] |
| } |
| } |