cycloevan's picture
Upload tokenizer/development_variants/opcode_5_250.json with huggingface_hub
3673148 verified
Raw History Blame Contribute Delete
21.7 kB
{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "[SEP]", "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 } ], "normalizer": { "type": "NFKC" }, "pre_tokenizer": { "type": "Whitespace" }, "post_processor": { "type": "TemplateProcessing", "single": [ { "SpecialToken": { "id": "[CLS]", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "[SEP]", "type_id": 0 } } ], "pair": [ { "SpecialToken": { "id": "[CLS]", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "[SEP]", "type_id": 0 } }, { "Sequence": { "id": "B", "type_id": 1 } }, { "SpecialToken": { "id": "[SEP]", "type_id": 1 } } ], "special_tokens": { "[CLS]": { "id": "[CLS]", "ids": [ 2 ], "tokens": [ "[CLS]" ] }, "[SEP]": { "id": "[SEP]", "ids": [ 3 ], "tokens": [ "[SEP]" ] } } }, "decoder": null, "model": { "type": "WordPiece", "unk_token": "[UNK]", "continuing_subword_prefix": "##", "max_input_chars_per_word": 100, "vocab": { "[PAD]": 0, "[UNK]": 1, "[CLS]": 2, "[SEP]": 3, "[MASK]": 4, ".": 5, "1": 6, "2": 7, "3": 8, "4": 9, "5": 10, "6": 11, "8": 12, "a": 13, "b": 14, "c": 15, "d": 16, "e": 17, "f": 18, "g": 19, "h": 20, "i": 21, "j": 22, "k": 23, "l": 24, "m": 25, "n": 26, "o": 27, "p": 28, "q": 29, "r": 30, "s": 31, "t": 32, "u": 33, "v": 34, "w": 35, "x": 36, "y": 37, "z": 38, "##d": 39, "##q": 40, "##e": 41, "##x": 42, "##t": 43, "##r": 44, "##a": 45, "##c": 46, "##o": 47, "##v": 48, "##s": 49, "##l": 50, "##i": 51, "##p": 52, "##b": 53, "##k": 54, "##w": 55, "##2": 56, "##m": 57, "##g": 58, "##u": 59, "##h": 60, "##n": 61, "##f": 62, "##z": 63, "##5": 64, "##6": 65, "##3": 66, "##1": 67, "##4": 68, "##y": 69, "##8": 70, "##ov": 71, "mov": 72, "##sh": 73, "pu": 74, "push": 75, "##ll": 76, "##all": 77, "call": 78, "##mp": 79, "##op": 80, "le": 81, "lea": 82, "pop": 83, "cmp": 84, "##st": 85, "##est": 86, "test": 87, "jz": 88, "##dd": 89, "add": 90, "##or": 91, "jn": 92, "xor": 93, "jnz": 94, "##et": 95, "jmp": 96, "ret": 97, "##ub": 98, "sub": 99, "##nd": 100, "and": 101, "in": 102, "inc": 103, "##zx": 104, "movzx": 105, "or": 106, "sh": 107, "nop": 108, "jc": 109, "jl": 110, "movs": 111, "##ps": 112, "##be": 113, "jbe": 114, "shr": 115, "##dq": 116, "##ul": 117, "js": 118, "##ec": 119, "dec": 120, "shl": 121, "ja": 122, "##mov": 123, "jnc": 124, "int": 125, "##mul": 126, "cmov": 127, "##ups": 128, "movups": 129, "int3": 130, "movsx": 131, "jg": 132, "jle": 133, "##ve": 134, "leave": 135, "imul": 136, "##ck": 137, "lo": 138, "sa": 139, "sar": 140, "sb": 141, "sbb": 142, "lock": 143, "set": 144, "ne": 145, "neg": 146, "movdq": 147, "##add": 148, "jns": 149, "##ld": 150, "movsd": 151, "jge": 152, "movsxd": 153, "##sd": 154, "##nz": 155, "cdq": 156, "##ch": 157, "movdqa": 158, "fst": 159, "fld": 160, "##iv": 161, "st": 162, "##chg": 163, "xadd": 164, "fstp": 165, "sto": 166, "mova": 167, "##dc": 168, "adc": 169, "mul": 170, "setnz": 171, "setz": 172, "xchg": 173, "stosd": 174, "xorps": 175, "movaps": 176, "##pd": 177, "re": 178, "rep": 179, "padd": 180, "movq": 181, "movdqu": 182, "##div": 183, "paddd": 184, "ps": 185, "idiv": 186, "no": 187, "not": 188, "cmova": 189, "cmovnz": 190, "div": 191, "psr": 192, "##sw": 193, "bt": 194, "cmovz": 195, "##nc": 196, "pa": 197, "##xchg": 198, "cmpxchg": 199, "cmovnc": 200, "pmul": 201, "##udq": 202, "pmuludq": 203, "##co": 204, "pand": 205, "psrld": 206, "cmovl": 207, "##xor": 208, "ror": 209, "ro": 210, "rol": 211, "fn": 212, "fnst": 213, "##sb": 214, "pxor": 215, "ud": 216, "ud2": 217, "cmovle": 218, "fnstsw": 219, "cmovc": 220, "##fd": 221, "##lpd": 222, "movapd": 223, "movlpd": 224, "##shu": 225, "##vt": 226, "cvt": 227, "psrl": 228, "movd": 229, "fco": 230, "fi": 231, "movss": 232, "##si": 233, "##np": 234, "pshu": 235, "fldz": 236, "##npck": 237, "stosb": 238, "psrlq": 239, "##ms": 240, "sha": 241, "psll": 242, "##cmp": 243, "##ss": 244, "pshufd": 245, "jp": 246, "fild": 247, "##npckh": 248, "##eq": 249, "pcmp": 250, "bts": 251, "fmul": 252, "rc": 253, "fcomp": 254, "setg": 255, "##cw": 256, "##sr": 257, "fadd": 258, "fx": 259, "##qdq": 260, "seto": 261, "##mi": 262, "punpckh": 263, "ae": 264, "punpckhqdq": 265, "stosw": 266, "mulsd": 267, "pslldq": 268, "pcmpeq": 269, "cvtsi": 270, "cvtsi2": 271, "addsd": 272, "##rnd": 273, "cdqe": 274, "vp": 275, "cmovbe": 276, "##id": 277, "cp": 278, "##uid": 279, "cpuid": 280, "setc": 281, "##ns": 282, "fxch": 283, "##ex": 284, "##msk": 285, "##movmsk": 286, "##movmskb": 287, "lod": 288, "sha1": 289, "cvtsi2sd": 290, "mulpd": 291, "##xc": 292, "##mxc": 293, "##mxcsr": 294, "vmov": 295, "movsb": 296, "rcr": 297, "shrd": 298, "pmovmskb": 299, "aes": 300, "vmovdq": 301, "fdiv": 302, "shld": 303, "cmovo": 304, "cmovg": 305, "fcom": 306, "##ca": 307, "cmovns": 308, "##25": 309, "sha25": 310, "sha256": 311, "##msg": 312, "##misd": 313, "##it": 314, "##ext": 315, "pcmpeqb": 316, "fld1": 317, "wa": 318, "wait": 319, "##enc": 320, "##ap": 321, "bsw": 322, "bswap": 323, "##rnds": 324, "addpd": 325, "pushfd": 326, "fstsw": 327, "jnp": 328, "fs": 329, "setl": 330, "fldcw": 331, "sca": 332, "seta": 333, "fu": 334, "fuco": 335, "cmovs": 336, "uco": 337, "cld": 338, "##ne": 339, "repne": 340, "andpd": 341, "btr": 342, "##nt": 343, "fch": 344, "fchs": 345, "##en": 346, "divsd": 347, "##2si": 348, "##ad": 349, "stmxcsr": 350, "cvtt": 351, "lodsd": 352, "vmovdqa": 353, "aesenc": 354, "scasb": 355, "co": 356, "paddq": 357, "pshuf": 358, "pext": 359, "pextr": 360, "ucomisd": 361, "##er": 362, "fsub": 363, "rcl": 364, "movsw": 365, "sha256rnds": 366, "sha256rnds2": 367, "sha1msg": 368, "por": 369, "fist": 370, "##sd2si": 371, "pextrw": 372, "cvttsd2si": 373, "bs": 374, "bsf": 375, "fstcw": 376, "psrldq": 377, "fa": 378, "##bs": 379, "fabs": 380, "fistp": 381, "ld": 382, "ldmxcsr": 383, "subsd": 384, "##as": 385, "##miss": 386, "frnd": 387, "##int": 388, "##dq2": 389, "cvtdq2": 390, "frndint": 391, "##hf": 392, "##ey": 393, "##key": 394, "##gen": 395, "##sist": 396, "aeskey": 397, "##assist": 398, "##genassist": 399, "aeskeygenassist": 400, "fucomp": 401, "sha256msg": 402, "vmovdqu": 403, "psllq": 404, "pcmpeqw": 405, "rd": 406, "pushad": 407, "lodsb": 408, "setge": 409, "comisd": 410, "unpckh": 411, "unpckhpd": 412, "##lw": 413, "##ri": 414, "##ist": 415, "pcmpist": 416, "vpxor": 417, "pcmpistri": 418, "sahf": 419, "##next": 420, "vpshu": 421, "sha1rnds": 422, "sha1next": 423, "sha1rnds4": 424, "sha1nexte": 425, "##le": 426, "fmulp": 427, "##li": 428, "subpd": 429, "mulss": 430, "##lex": 431, "pshuflw": 432, "orpd": 433, "fnstcw": 434, "unpck": 435, "bsr": 436, "punpck": 437, "cvtdq2ps": 438, "addss": 439, "fucom": 440, "faddp": 441, "fucompp": 442, "fnc": 443, "fnclex": 444, "fdivr": 445, "std": 446, "unpcklpd": 447, "##se": 448, "##fenc": 449, "##fence": 450, "popad": 451, "punpckl": 452, "sha1msg2": 453, "sha1msg1": 454, "fcompp": 455, "##ou": 456, "##env": 457, "##sdec": 458, "aesdec": 459, "vz": 460, "##pp": 461, "##erou": 462, "vzerou": 463, "##pper": 464, "vzeroupper": 465, "vpshufd": 466, "comiss": 467, "setns": 468, "fsubr": 469, "##gn": 470, "pali": 471, "pshufb": 472, "##gnr": 473, "palignr": 474, "##uf": 475, "shuf": 476, "xorpd": 477, "setbe": 478, "##ts": 479, "rdts": 480, "rdtsc": 481, "shufps": 482, "cmpeq": 483, "cmpeqsd": 484, "##use": 485, "pause": 486, "##bv": 487, "##etbv": 488, "xg": 489, "xgetbv": 490, "ou": 491, "out": 492, "##bw": 493, "##re": 494, "vpadd": 495, "cmovge": 496, "setnc": 497, "##hps": 498, "sha256msg2": 499, "sha256msg1": 500, "loop": 501, "vpaddd": 502, "lfence": 503, "##wd": 504, "cwd": 505, "cwde": 506, "lodsw": 507, "movl": 508, "movlhps": 509, "ucomiss": 510, "##la": 511, "divss": 512, "vpcmp": 513, "vpcmpeq": 514, "cq": 515, "cqo": 516, "##in": 517, "##cale": 518, "fscale": 519, "fdivrp": 520, "cvtsi2ss": 521, "vpmovmskb": 522, "##2x": 523, "##insr": 524, "pinsr": 525, "vps": 526, "##lc": 527, "movnt": 528, "punpckldq": 529, "##ss2si": 530, "subss": 531, "scasw": 532, "cvttss2si": 533, "pslld": 534, "popfd": 535, "clc": 536, "fdivp": 537, "##mc": 538, "sets": 539, "fldenv": 540, "fnstenv": 541, "cmpn": 542, "fiadd": 543, "##am": 544, "fy": 545, "##l2x": 546, "fyl2x": 547, "repe": 548, "fxam": 549, "psub": 550, "cvtdq2pd": 551, "##2pd": 552, "cmpnle": 553, "cvtps": 554, "cvtps2pd": 555, "btc": 556, "retf": 557, "vpcmpeqb": 558, "##simc": 559, "aesimc": 560, "punpcklbw": 561, "cmpnlepd": 562, "cmpsb": 563, "cbw": 564, "xla": 565, "xlat": 566, "##pi": 567, "fldpi": 568, "pre": 569, "##fet": 570, "##chw": 571, "prefet": 572, "prefetchw": 573, "##8b": 574, "cmpxchg8b": 575, "pandn": 576, "##xz": 577, "psubd": 578, "jno": 579, "ff": 580, "##ss2": 581, "##ree": 582, "ffree": 583, "cvtss2": 584, "cvtss2sd": 585, "jo": 586, "##fq": 587, "la": 588, "lahf": 589, "##sq": 590, "##lps": 591, "##rst": 592, "stosq": 593, "##rstor": 594, "setle": 595, "##fb": 596, "##lld": 597, "fldl": 598, "vpshufb": 599, "##last": 600, "pinsrd": 601, "##rld": 602, "vpslld": 603, "vpsrld": 604, "##ave": 605, "##and": 606, "jec": 607, "jecxz": 608, "movntps": 609, "##rand": 610, "rdrand": 611, "fidiv": 612, "##64": 613, "cli": 614, "sfence": 615, "pextrd": 616, "outsd": 617, "vxor": 618, "##lt": 619, "vxorps": 620, "vpcmpeqw": 621, "mulps": 622, "##sd2": 623, "##rc": 624, "cvtsd2": 625, "cvtsd2ss": 626, "##g2": 627, "fsubrp": 628, "fldlg2": 629, "##2ps": 630, "##pd2ps": 631, "cvtpd2ps": 632, "pushfq": 633, "##mip": 634, "setnp": 635, "vmovnt": 636, "fsubp": 637, "fucomip": 638, "movh": 639, "aesenclast": 640, "movhlps": 641, "vmovdqu64": 642, "##cnt": 643, "##ed": 644, "popcnt": 645, "rdse": 646, "rdseed": 647, "##qr": 648, "##qrt": 649, "##tp": 650, "##m1": 651, "fisttp": 652, "andps": 653, "sti": 654, "movntdq": 655, "pinsrw": 656, "crc": 657, "##32": 658, "cmplt": 659, "crc32": 660, "fsqrt": 661, "##ro": 662, "##ast": 663, "##adc": 664, "##bro": 665, "##msr": 666, "vpbro": 667, "##adcast": 668, "vpbroadcast": 669, "fxrstor": 670, "f2x": 671, "frstor": 672, "f2xm1": 673, "##aw": 674, "psraw": 675, "vmovntdq": 676, "fsave": 677, "##lwd": 678, "punpcklwd": 679, "fp": 680, "##save": 681, "pcmpeqd": 682, "addps": 683, "fxsave": 684, "outsb": 685, "cmpltpd": 686, "kmov": 687, "bz": 688, "vi": 689, "##tf": 690, "##28": 691, "##hi": 692, "##128": 693, "##nser": 694, "vpbroadcastd": 695, "kmovd": 696, "bzhi": 697, "vinser": 698, "##tf128": 699, "vinsertf128": 700, "pb": 701, "##ndw": 702, "##lendw": 703, "movnti": 704, "pblendw": 705, "##stp": 706, "loopnz": 707, "ad": 708, "##ox": 709, "adcx": 710, "mulx": 711, "unpcklps": 712, "adox": 713, "cmpsd": 714, "fc": 715, "fb": 716, "##hw": 717, "cmc": 718, "ir": 719, "##gt": 720, "fimul": 721, "iret": 722, "pcmpgt": 723, "pinsrb": 724, "fbstp": 725, "##mu": 726, "fpre": 727, "popfq": 728, "insb": 729, "aesdeclast": 730, "##sub": 731, "cmpsw": 732, "fisub": 733, "pc": 734, "fclex": 735, "pcl": 736, "ent": 737, "ma": 738, "enter": 739, "max": 740, "pshufhw": 741, "pcmpgtd": 742, "##mull": 743, "wr": 744, "rdmsr": 745, "wrmsr": 746, "into": 747, "subps": 748, "scasd": 749, "sw": 750, "##gs": 751, "##apgs": 752, "swapgs": 753, "insd": 754, "fprem": 755, "stc": 756, "jrc": 757, "##n2": 758, "fldln2": 759, "jrcxz": 760, "##unpck": 761, "kunpck": 762, "##aps": 763, "movhps": 764, "vmovaps": 765, "vmovdqa64": 766, "vmovdqu8": 767, "vmovntps": 768, "kunpckdq": 769, "hlt": 770, "jmpf": 771, "loopz": 772, "##nit": 773, "psrad": 774, "finit": 775, "iretd": 776, "iretq": 777, "pclmull": 778, "pclmullq": 779, "##lqdq": 780, "maxss": 781, "salc": 782, "min": 783, "int1": 784, "vmovd": 785, "pclmullqlqdq": 786, "punpcklqdq": 787, "psubq": 788, "pclmul": 789, "##hqdq": 790, "paddsw": 791, "em": 792, "##hq": 793, "pack": 794, "pclmulhq": 795, "emms": 796, "##ta": 797, "##test": 798, "##estri": 799, "##ldt": 800, "pcmpestri": 801, "vptest": 802, "vpaddq": 803, "vpbroadcastb": 804, "##tan": 805, "pmull": 806, "sldt": 807, "pmullw": 808, "mfence": 809, "##aa": 810, "fcos": 811, "pshufw": 812, "minss": 813, "##atan": 814, "fico": 815, "psubsw": 816, "fpatan": 817, "pclmulhqhqdq": 818, "das": 819, "cvtsd2si": 820, "fprem1": 821, "fisubr": 822, "aas": 823, "bou": 824, "pm": 825, "##addwd": 826, "bound": 827, "pmaddwd": 828, "ar": 829, "##pl": 830, "##usw": 831, "cmpnlesd": 832, "cmpltsd": 833, "maxps": 834, "arpl": 835, "cmple": 836, "orps": 837, "shufpd": 838, "cmpleps": 839, "fsi": 840, "movsq": 841, "divps": 842, "pmulhw": 843, "fsin": 844, "##usb": 845, "fcomip": 846, "punpckhbw": 847, "sqrt": 848, "##mq": 849, "movmsk": 850, "vper": 851, "fcmov": 852, "packs": 853, "ficom": 854, "movmskps": 855, "vpermq": 856, "aaa": 857, "vc": 858, "paddb": 859, "vpand": 860, "pinsrq": 861, "cmpnlt": 862, "packusw": 863, "vcvt": 864, "cmpnltsd": 865, "packuswb": 866, "pmu": 867, "##nps": 868, "callf": 869, "andnps": 870, "paddw": 871, "##ncstp": 872, "fincstp": 873, "psubusb": 874, "fidivr": 875, "pcmpgtb": 876, "pmulld": 877, "daa": 878, "##tr": 879, "maxsd": 880, "aad": 881, "##ac": 882, "les": 883, "fxtr": 884, "##idt": 885, "cmpneq": 886, "##act": 887, "fxtract": 888, "##sdw": 889, "fcomi": 890, "psllw": 891, "minsd": 892, "ficomp": 893, "sqrtps": 894, "packssdw": 895, "ft": 896, "##vl": 897, "##pg": 898, "##usi": 899, "invl": 900, "paddsb": 901, "fucomi": 902, "lds": 903, "fcmovn": 904, "vcvtt": 905, "cmpneqps": 906, "ftst": 907, "invlpg": 908, "sidt": 909, "##qq": 910, "paddusw": 911, "##swb": 912, "punpckhdq": 913, "vpinsr": 914, "pclmullqhqdq": 915, "packsswb": 916, "vcvtqq": 917, "vpinsrd": 918, "vcvtqq2pd": 919, "xc": 920, "##dt": 921, "##ry": 922, "##pt": 923, "##gdt": 924, "punpckhwd": 925, "cmpnless": 926, "##sd2usi": 927, "cmpltss": 928, "fbld": 929, "pclmulhqlqdq": 930, "sqrtsd": 931, "vcvttsd2usi": 932, "xcry": 933, "xcrypt": 934, "aam": 935, "lidt": 936, "sgdt": 937, "wb": 938, "xs": 939, "##vd": 940, "##6b": 941, "##16b": 942, "str": 943, "paddusb": 944, "psad": 945, "cmpxchg16b": 946, "##invd": 947, "psubb": 948, "fptan": 949, "fcmovne": 950, "fcmovnb": 951, "wbinvd": 952, "xsetbv": 953, "psadbw": 954, "cl": 955, "##lu": 956, "##2e": 957, "##flu": 958, "cvtss2si": 959, "cvtpi": 960, "psrlw": 961, "scasq": 962, "unpckhps": 963, "##mcall": 964, "psubw": 965, "##ss2usi": 966, "fldl2e": 967, "movhpd": 968, "cmpltps": 969, "pclmulqdq": 970, "cmpneqpd": 971, "fcmovnu": 972, "vcvttss2usi": 973, "xcryptc": 974, "clflu": 975, "cvtpi2ps": 976, "clflush": 977 } } }
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "[PAD]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "[UNK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "[CLS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "[SEP]",
"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
}
],
"normalizer": {
"type": "NFKC"
},
"pre_tokenizer": {
"type": "Whitespace"
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "[CLS]",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "[SEP]",
"type_id": 0
}
}
],
"pair": [
{
"SpecialToken": {
"id": "[CLS]",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "[SEP]",
"type_id": 0
}
},
{
"Sequence": {