Pretrain_TransVi_5 / tokenizer.json
Priyasi's picture
Upload 12 files
aafd5f6 verified
Raw History Blame Contribute Delete
23.4 kB
{
"version": "1.0",
"truncation": {
"direction": "Right",
"max_length": 512,
"strategy": "LongestFirst",
"stride": 0
},
"padding": {
"strategy": {
"Fixed": 512
},
"direction": "Right",
"pad_to_multiple_of": null,
"pad_id": 0,
"pad_type_id": 0,
"pad_token": "[PAD]"
},
"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": "BertNormalizer",
"clean_text": true,
"handle_chinese_chars": true,
"strip_accents": null,
"lowercase": false
},
"pre_tokenizer": {
"type": "BertPreTokenizer"
},
"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": {
"type": "WordPiece",
"prefix": "##",
"cleanup": true
},
"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,
"AAAAA": 5,
"AAAAT": 6,
"AAAAC": 7,
"AAAAG": 8,
"AAATA": 9,
"AAATT": 10,
"AAATC": 11,
"AAATG": 12,
"AAACA": 13,
"AAACT": 14,
"AAACC": 15,
"AAACG": 16,
"AAAGA": 17,
"AAAGT": 18,
"AAAGC": 19,
"AAAGG": 20,
"AATAA": 21,
"AATAT": 22,
"AATAC": 23,
"AATAG": 24,
"AATTA": 25,
"AATTT": 26,
"AATTC": 27,
"AATTG": 28,
"AATCA": 29,
"AATCT": 30,
"AATCC": 31,
"AATCG": 32,
"AATGA": 33,
"AATGT": 34,
"AATGC": 35,
"AATGG": 36,
"AACAA": 37,
"AACAT": 38,
"AACAC": 39,
"AACAG": 40,
"AACTA": 41,
"AACTT": 42,
"AACTC": 43,
"AACTG": 44,
"AACCA": 45,
"AACCT": 46,
"AACCC": 47,
"AACCG": 48,
"AACGA": 49,
"AACGT": 50,
"AACGC": 51,
"AACGG": 52,
"AAGAA": 53,
"AAGAT": 54,
"AAGAC": 55,
"AAGAG": 56,
"AAGTA": 57,
"AAGTT": 58,
"AAGTC": 59,
"AAGTG": 60,
"AAGCA": 61,
"AAGCT": 62,
"AAGCC": 63,
"AAGCG": 64,
"AAGGA": 65,
"AAGGT": 66,
"AAGGC": 67,
"AAGGG": 68,
"ATAAA": 69,
"ATAAT": 70,
"ATAAC": 71,
"ATAAG": 72,
"ATATA": 73,
"ATATT": 74,
"ATATC": 75,
"ATATG": 76,
"ATACA": 77,
"ATACT": 78,
"ATACC": 79,
"ATACG": 80,
"ATAGA": 81,
"ATAGT": 82,
"ATAGC": 83,
"ATAGG": 84,
"ATTAA": 85,
"ATTAT": 86,
"ATTAC": 87,
"ATTAG": 88,
"ATTTA": 89,
"ATTTT": 90,
"ATTTC": 91,
"ATTTG": 92,
"ATTCA": 93,
"ATTCT": 94,
"ATTCC": 95,
"ATTCG": 96,
"ATTGA": 97,
"ATTGT": 98,
"ATTGC": 99,
"ATTGG": 100,
"ATCAA": 101,
"ATCAT": 102,
"ATCAC": 103,
"ATCAG": 104,
"ATCTA": 105,
"ATCTT": 106,
"ATCTC": 107,
"ATCTG": 108,
"ATCCA": 109,
"ATCCT": 110,
"ATCCC": 111,
"ATCCG": 112,
"ATCGA": 113,
"ATCGT": 114,
"ATCGC": 115,
"ATCGG": 116,
"ATGAA": 117,
"ATGAT": 118,
"ATGAC": 119,
"ATGAG": 120,
"ATGTA": 121,
"ATGTT": 122,
"ATGTC": 123,
"ATGTG": 124,
"ATGCA": 125,
"ATGCT": 126,
"ATGCC": 127,
"ATGCG": 128,
"ATGGA": 129,
"ATGGT": 130,
"ATGGC": 131,
"ATGGG": 132,
"ACAAA": 133,
"ACAAT": 134,
"ACAAC": 135,
"ACAAG": 136,
"ACATA": 137,
"ACATT": 138,
"ACATC": 139,
"ACATG": 140,
"ACACA": 141,
"ACACT": 142,
"ACACC": 143,
"ACACG": 144,
"ACAGA": 145,
"ACAGT": 146,
"ACAGC": 147,
"ACAGG": 148,
"ACTAA": 149,
"ACTAT": 150,
"ACTAC": 151,
"ACTAG": 152,
"ACTTA": 153,
"ACTTT": 154,
"ACTTC": 155,
"ACTTG": 156,
"ACTCA": 157,
"ACTCT": 158,
"ACTCC": 159,
"ACTCG": 160,
"ACTGA": 161,
"ACTGT": 162,
"ACTGC": 163,
"ACTGG": 164,
"ACCAA": 165,
"ACCAT": 166,
"ACCAC": 167,
"ACCAG": 168,
"ACCTA": 169,
"ACCTT": 170,
"ACCTC": 171,
"ACCTG": 172,
"ACCCA": 173,
"ACCCT": 174,
"ACCCC": 175,
"ACCCG": 176,
"ACCGA": 177,
"ACCGT": 178,
"ACCGC": 179,
"ACCGG": 180,
"ACGAA": 181,
"ACGAT": 182,
"ACGAC": 183,
"ACGAG": 184,
"ACGTA": 185,
"ACGTT": 186,
"ACGTC": 187,
"ACGTG": 188,
"ACGCA": 189,
"ACGCT": 190,
"ACGCC": 191,
"ACGCG": 192,
"ACGGA": 193,
"ACGGT": 194,
"ACGGC": 195,
"ACGGG": 196,
"AGAAA": 197,
"AGAAT": 198,
"AGAAC": 199,
"AGAAG": 200,
"AGATA": 201,
"AGATT": 202,
"AGATC": 203,
"AGATG": 204,
"AGACA": 205,
"AGACT": 206,
"AGACC": 207,
"AGACG": 208,
"AGAGA": 209,
"AGAGT": 210,
"AGAGC": 211,
"AGAGG": 212,
"AGTAA": 213,
"AGTAT": 214,
"AGTAC": 215,
"AGTAG": 216,
"AGTTA": 217,
"AGTTT": 218,
"AGTTC": 219,
"AGTTG": 220,
"AGTCA": 221,
"AGTCT": 222,
"AGTCC": 223,
"AGTCG": 224,
"AGTGA": 225,
"AGTGT": 226,
"AGTGC": 227,
"AGTGG": 228,
"AGCAA": 229,
"AGCAT": 230,
"AGCAC": 231,
"AGCAG": 232,
"AGCTA": 233,
"AGCTT": 234,
"AGCTC": 235,
"AGCTG": 236,
"AGCCA": 237,
"AGCCT": 238,
"AGCCC": 239,
"AGCCG": 240,
"AGCGA": 241,
"AGCGT": 242,
"AGCGC": 243,
"AGCGG": 244,
"AGGAA": 245,
"AGGAT": 246,
"AGGAC": 247,
"AGGAG": 248,
"AGGTA": 249,
"AGGTT": 250,
"AGGTC": 251,
"AGGTG": 252,
"AGGCA": 253,
"AGGCT": 254,
"AGGCC": 255,
"AGGCG": 256,
"AGGGA": 257,
"AGGGT": 258,
"AGGGC": 259,
"AGGGG": 260,
"TAAAA": 261,
"TAAAT": 262,
"TAAAC": 263,
"TAAAG": 264,
"TAATA": 265,
"TAATT": 266,
"TAATC": 267,
"TAATG": 268,
"TAACA": 269,
"TAACT": 270,
"TAACC": 271,
"TAACG": 272,
"TAAGA": 273,
"TAAGT": 274,
"TAAGC": 275,
"TAAGG": 276,
"TATAA": 277,
"TATAT": 278,
"TATAC": 279,
"TATAG": 280,
"TATTA": 281,
"TATTT": 282,
"TATTC": 283,
"TATTG": 284,
"TATCA": 285,
"TATCT": 286,
"TATCC": 287,
"TATCG": 288,
"TATGA": 289,
"TATGT": 290,
"TATGC": 291,
"TATGG": 292,
"TACAA": 293,
"TACAT": 294,
"TACAC": 295,
"TACAG": 296,
"TACTA": 297,
"TACTT": 298,
"TACTC": 299,
"TACTG": 300,
"TACCA": 301,
"TACCT": 302,
"TACCC": 303,
"TACCG": 304,
"TACGA": 305,
"TACGT": 306,
"TACGC": 307,
"TACGG": 308,
"TAGAA": 309,
"TAGAT": 310,
"TAGAC": 311,
"TAGAG": 312,
"TAGTA": 313,
"TAGTT": 314,
"TAGTC": 315,
"TAGTG": 316,
"TAGCA": 317,
"TAGCT": 318,
"TAGCC": 319,
"TAGCG": 320,
"TAGGA": 321,
"TAGGT": 322,
"TAGGC": 323,
"TAGGG": 324,
"TTAAA": 325,
"TTAAT": 326,
"TTAAC": 327,
"TTAAG": 328,
"TTATA": 329,
"TTATT": 330,
"TTATC": 331,
"TTATG": 332,
"TTACA": 333,
"TTACT": 334,
"TTACC": 335,
"TTACG": 336,
"TTAGA": 337,
"TTAGT": 338,
"TTAGC": 339,
"TTAGG": 340,
"TTTAA": 341,
"TTTAT": 342,
"TTTAC": 343,
"TTTAG": 344,
"TTTTA": 345,
"TTTTT": 346,
"TTTTC": 347,
"TTTTG": 348,
"TTTCA": 349,
"TTTCT": 350,
"TTTCC": 351,
"TTTCG": 352,
"TTTGA": 353,
"TTTGT": 354,
"TTTGC": 355,
"TTTGG": 356,
"TTCAA": 357,
"TTCAT": 358,
"TTCAC": 359,
"TTCAG": 360,
"TTCTA": 361,
"TTCTT": 362,
"TTCTC": 363,
"TTCTG": 364,
"TTCCA": 365,
"TTCCT": 366,
"TTCCC": 367,
"TTCCG": 368,
"TTCGA": 369,
"TTCGT": 370,
"TTCGC": 371,
"TTCGG": 372,
"TTGAA": 373,
"TTGAT": 374,
"TTGAC": 375,
"TTGAG": 376,
"TTGTA": 377,
"TTGTT": 378,
"TTGTC": 379,
"TTGTG": 380,
"TTGCA": 381,
"TTGCT": 382,
"TTGCC": 383,
"TTGCG": 384,
"TTGGA": 385,
"TTGGT": 386,
"TTGGC": 387,
"TTGGG": 388,
"TCAAA": 389,
"TCAAT": 390,
"TCAAC": 391,
"TCAAG": 392,
"TCATA": 393,
"TCATT": 394,
"TCATC": 395,
"TCATG": 396,
"TCACA": 397,
"TCACT": 398,
"TCACC": 399,
"TCACG": 400,
"TCAGA": 401,
"TCAGT": 402,
"TCAGC": 403,
"TCAGG": 404,
"TCTAA": 405,
"TCTAT": 406,
"TCTAC": 407,
"TCTAG": 408,
"TCTTA": 409,
"TCTTT": 410,
"TCTTC": 411,
"TCTTG": 412,
"TCTCA": 413,
"TCTCT": 414,
"TCTCC": 415,
"TCTCG": 416,
"TCTGA": 417,
"TCTGT": 418,
"TCTGC": 419,
"TCTGG": 420,
"TCCAA": 421,
"TCCAT": 422,
"TCCAC": 423,
"TCCAG": 424,
"TCCTA": 425,
"TCCTT": 426,
"TCCTC": 427,
"TCCTG": 428,
"TCCCA": 429,
"TCCCT": 430,
"TCCCC": 431,
"TCCCG": 432,
"TCCGA": 433,
"TCCGT": 434,
"TCCGC": 435,
"TCCGG": 436,
"TCGAA": 437,
"TCGAT": 438,
"TCGAC": 439,
"TCGAG": 440,
"TCGTA": 441,
"TCGTT": 442,
"TCGTC": 443,
"TCGTG": 444,
"TCGCA": 445,
"TCGCT": 446,
"TCGCC": 447,
"TCGCG": 448,
"TCGGA": 449,
"TCGGT": 450,
"TCGGC": 451,
"TCGGG": 452,
"TGAAA": 453,
"TGAAT": 454,
"TGAAC": 455,
"TGAAG": 456,
"TGATA": 457,
"TGATT": 458,
"TGATC": 459,
"TGATG": 460,
"TGACA": 461,
"TGACT": 462,
"TGACC": 463,
"TGACG": 464,
"TGAGA": 465,
"TGAGT": 466,
"TGAGC": 467,
"TGAGG": 468,
"TGTAA": 469,
"TGTAT": 470,
"TGTAC": 471,
"TGTAG": 472,
"TGTTA": 473,
"TGTTT": 474,
"TGTTC": 475,
"TGTTG": 476,
"TGTCA": 477,
"TGTCT": 478,
"TGTCC": 479,
"TGTCG": 480,
"TGTGA": 481,
"TGTGT": 482,
"TGTGC": 483,
"TGTGG": 484,
"TGCAA": 485,
"TGCAT": 486,
"TGCAC": 487,
"TGCAG": 488,
"TGCTA": 489,
"TGCTT": 490,
"TGCTC": 491,
"TGCTG": 492,
"TGCCA": 493,
"TGCCT": 494,
"TGCCC": 495,
"TGCCG": 496,
"TGCGA": 497,
"TGCGT": 498,
"TGCGC": 499,
"TGCGG": 500,
"TGGAA": 501,
"TGGAT": 502,
"TGGAC": 503,
"TGGAG": 504,
"TGGTA": 505,
"TGGTT": 506,
"TGGTC": 507,
"TGGTG": 508,
"TGGCA": 509,
"TGGCT": 510,
"TGGCC": 511,
"TGGCG": 512,
"TGGGA": 513,
"TGGGT": 514,
"TGGGC": 515,
"TGGGG": 516,
"CAAAA": 517,
"CAAAT": 518,
"CAAAC": 519,
"CAAAG": 520,
"CAATA": 521,
"CAATT": 522,
"CAATC": 523,
"CAATG": 524,
"CAACA": 525,
"CAACT": 526,
"CAACC": 527,
"CAACG": 528,
"CAAGA": 529,
"CAAGT": 530,
"CAAGC": 531,
"CAAGG": 532,
"CATAA": 533,
"CATAT": 534,
"CATAC": 535,
"CATAG": 536,
"CATTA": 537,
"CATTT": 538,
"CATTC": 539,
"CATTG": 540,
"CATCA": 541,
"CATCT": 542,
"CATCC": 543,
"CATCG": 544,
"CATGA": 545,
"CATGT": 546,
"CATGC": 547,
"CATGG": 548,
"CACAA": 549,
"CACAT": 550,
"CACAC": 551,
"CACAG": 552,
"CACTA": 553,
"CACTT": 554,
"CACTC": 555,
"CACTG": 556,
"CACCA": 557,
"CACCT": 558,
"CACCC": 559,
"CACCG": 560,
"CACGA": 561,
"CACGT": 562,
"CACGC": 563,
"CACGG": 564,
"CAGAA": 565,
"CAGAT": 566,
"CAGAC": 567,
"CAGAG": 568,
"CAGTA": 569,
"CAGTT": 570,
"CAGTC": 571,
"CAGTG": 572,
"CAGCA": 573,
"CAGCT": 574,
"CAGCC": 575,
"CAGCG": 576,
"CAGGA": 577,
"CAGGT": 578,
"CAGGC": 579,
"CAGGG": 580,
"CTAAA": 581,
"CTAAT": 582,
"CTAAC": 583,
"CTAAG": 584,
"CTATA": 585,
"CTATT": 586,
"CTATC": 587,
"CTATG": 588,
"CTACA": 589,
"CTACT": 590,
"CTACC": 591,
"CTACG": 592,
"CTAGA": 593,
"CTAGT": 594,
"CTAGC": 595,
"CTAGG": 596,
"CTTAA": 597,
"CTTAT": 598,
"CTTAC": 599,
"CTTAG": 600,
"CTTTA": 601,
"CTTTT": 602,
"CTTTC": 603,
"CTTTG": 604,
"CTTCA": 605,
"CTTCT": 606,
"CTTCC": 607,
"CTTCG": 608,
"CTTGA": 609,
"CTTGT": 610,
"CTTGC": 611,
"CTTGG": 612,
"CTCAA": 613,
"CTCAT": 614,
"CTCAC": 615,
"CTCAG": 616,
"CTCTA": 617,
"CTCTT": 618,
"CTCTC": 619,
"CTCTG": 620,
"CTCCA": 621,
"CTCCT": 622,
"CTCCC": 623,
"CTCCG": 624,
"CTCGA": 625,
"CTCGT": 626,
"CTCGC": 627,
"CTCGG": 628,
"CTGAA": 629,
"CTGAT": 630,
"CTGAC": 631,
"CTGAG": 632,
"CTGTA": 633,
"CTGTT": 634,
"CTGTC": 635,
"CTGTG": 636,
"CTGCA": 637,
"CTGCT": 638,
"CTGCC": 639,
"CTGCG": 640,
"CTGGA": 641,
"CTGGT": 642,
"CTGGC": 643,
"CTGGG": 644,
"CCAAA": 645,
"CCAAT": 646,
"CCAAC": 647,
"CCAAG": 648,
"CCATA": 649,
"CCATT": 650,
"CCATC": 651,
"CCATG": 652,
"CCACA": 653,
"CCACT": 654,
"CCACC": 655,
"CCACG": 656,
"CCAGA": 657,
"CCAGT": 658,
"CCAGC": 659,
"CCAGG": 660,
"CCTAA": 661,
"CCTAT": 662,
"CCTAC": 663,
"CCTAG": 664,
"CCTTA": 665,
"CCTTT": 666,
"CCTTC": 667,
"CCTTG": 668,
"CCTCA": 669,
"CCTCT": 670,
"CCTCC": 671,
"CCTCG": 672,
"CCTGA": 673,
"CCTGT": 674,
"CCTGC": 675,
"CCTGG": 676,
"CCCAA": 677,
"CCCAT": 678,
"CCCAC": 679,
"CCCAG": 680,
"CCCTA": 681,
"CCCTT": 682,
"CCCTC": 683,
"CCCTG": 684,
"CCCCA": 685,
"CCCCT": 686,
"CCCCC": 687,
"CCCCG": 688,
"CCCGA": 689,
"CCCGT": 690,
"CCCGC": 691,
"CCCGG": 692,
"CCGAA": 693,
"CCGAT": 694,
"CCGAC": 695,
"CCGAG": 696,
"CCGTA": 697,
"CCGTT": 698,
"CCGTC": 699,
"CCGTG": 700,
"CCGCA": 701,
"CCGCT": 702,
"CCGCC": 703,
"CCGCG": 704,
"CCGGA": 705,
"CCGGT": 706,
"CCGGC": 707,
"CCGGG": 708,
"CGAAA": 709,
"CGAAT": 710,
"CGAAC": 711,
"CGAAG": 712,
"CGATA": 713,
"CGATT": 714,
"CGATC": 715,
"CGATG": 716,
"CGACA": 717,
"CGACT": 718,
"CGACC": 719,
"CGACG": 720,
"CGAGA": 721,
"CGAGT": 722,
"CGAGC": 723,
"CGAGG": 724,
"CGTAA": 725,
"CGTAT": 726,
"CGTAC": 727,
"CGTAG": 728,
"CGTTA": 729,
"CGTTT": 730,
"CGTTC": 731,
"CGTTG": 732,
"CGTCA": 733,
"CGTCT": 734,
"CGTCC": 735,
"CGTCG": 736,
"CGTGA": 737,
"CGTGT": 738,
"CGTGC": 739,
"CGTGG": 740,
"CGCAA": 741,
"CGCAT": 742,
"CGCAC": 743,
"CGCAG": 744,
"CGCTA": 745,
"CGCTT": 746,
"CGCTC": 747,
"CGCTG": 748,
"CGCCA": 749,
"CGCCT": 750,
"CGCCC": 751,
"CGCCG": 752,
"CGCGA": 753,
"CGCGT": 754,
"CGCGC": 755,
"CGCGG": 756,
"CGGAA": 757,
"CGGAT": 758,
"CGGAC": 759,
"CGGAG": 760,
"CGGTA": 761,
"CGGTT": 762,
"CGGTC": 763,
"CGGTG": 764,
"CGGCA": 765,
"CGGCT": 766,
"CGGCC": 767,
"CGGCG": 768,
"CGGGA": 769,
"CGGGT": 770,
"CGGGC": 771,
"CGGGG": 772,
"GAAAA": 773,
"GAAAT": 774,
"GAAAC": 775,
"GAAAG": 776,
"GAATA": 777,
"GAATT": 778,
"GAATC": 779,
"GAATG": 780,
"GAACA": 781,
"GAACT": 782,
"GAACC": 783,
"GAACG": 784,
"GAAGA": 785,
"GAAGT": 786,
"GAAGC": 787,
"GAAGG": 788,
"GATAA": 789,
"GATAT": 790,
"GATAC": 791,
"GATAG": 792,
"GATTA": 793,
"GATTT": 794,
"GATTC": 795,
"GATTG": 796,
"GATCA": 797,
"GATCT": 798,
"GATCC": 799,
"GATCG": 800,
"GATGA": 801,
"GATGT": 802,
"GATGC": 803,
"GATGG": 804,
"GACAA": 805,
"GACAT": 806,
"GACAC": 807,
"GACAG": 808,
"GACTA": 809,
"GACTT": 810,
"GACTC": 811,
"GACTG": 812,
"GACCA": 813,
"GACCT": 814,
"GACCC": 815,
"GACCG": 816,
"GACGA": 817,
"GACGT": 818,
"GACGC": 819,
"GACGG": 820,
"GAGAA": 821,
"GAGAT": 822,
"GAGAC": 823,
"GAGAG": 824,
"GAGTA": 825,
"GAGTT": 826,
"GAGTC": 827,
"GAGTG": 828,
"GAGCA": 829,
"GAGCT": 830,
"GAGCC": 831,
"GAGCG": 832,
"GAGGA": 833,
"GAGGT": 834,
"GAGGC": 835,
"GAGGG": 836,
"GTAAA": 837,
"GTAAT": 838,
"GTAAC": 839,
"GTAAG": 840,
"GTATA": 841,
"GTATT": 842,
"GTATC": 843,
"GTATG": 844,
"GTACA": 845,
"GTACT": 846,
"GTACC": 847,
"GTACG": 848,
"GTAGA": 849,
"GTAGT": 850,
"GTAGC": 851,
"GTAGG": 852,
"GTTAA": 853,
"GTTAT": 854,
"GTTAC": 855,
"GTTAG": 856,
"GTTTA": 857,
"GTTTT": 858,
"GTTTC": 859,
"GTTTG": 860,
"GTTCA": 861,
"GTTCT": 862,
"GTTCC": 863,
"GTTCG": 864,
"GTTGA": 865,
"GTTGT": 866,
"GTTGC": 867,
"GTTGG": 868,
"GTCAA": 869,
"GTCAT": 870,
"GTCAC": 871,
"GTCAG": 872,
"GTCTA": 873,
"GTCTT": 874,
"GTCTC": 875,
"GTCTG": 876,
"GTCCA": 877,
"GTCCT": 878,
"GTCCC": 879,
"GTCCG": 880,
"GTCGA": 881,
"GTCGT": 882,
"GTCGC": 883,
"GTCGG": 884,
"GTGAA": 885,
"GTGAT": 886,
"GTGAC": 887,
"GTGAG": 888,
"GTGTA": 889,
"GTGTT": 890,
"GTGTC": 891,
"GTGTG": 892,
"GTGCA": 893,
"GTGCT": 894,
"GTGCC": 895,
"GTGCG": 896,
"GTGGA": 897,
"GTGGT": 898,
"GTGGC": 899,
"GTGGG": 900,
"GCAAA": 901,
"GCAAT": 902,
"GCAAC": 903,
"GCAAG": 904,
"GCATA": 905,
"GCATT": 906,
"GCATC": 907,
"GCATG": 908,
"GCACA": 909,
"GCACT": 910,
"GCACC": 911,
"GCACG": 912,
"GCAGA": 913,
"GCAGT": 914,
"GCAGC": 915,
"GCAGG": 916,
"GCTAA": 917,
"GCTAT": 918,
"GCTAC": 919,
"GCTAG": 920,
"GCTTA": 921,
"GCTTT": 922,
"GCTTC": 923,
"GCTTG": 924,
"GCTCA": 925,
"GCTCT": 926,
"GCTCC": 927,
"GCTCG": 928,
"GCTGA": 929,
"GCTGT": 930,
"GCTGC": 931,
"GCTGG": 932,
"GCCAA": 933,
"GCCAT": 934,
"GCCAC": 935,
"GCCAG": 936,
"GCCTA": 937,
"GCCTT": 938,
"GCCTC": 939,
"GCCTG": 940,
"GCCCA": 941,
"GCCCT": 942,
"GCCCC": 943,
"GCCCG": 944,
"GCCGA": 945,
"GCCGT": 946,
"GCCGC": 947,
"GCCGG": 948,
"GCGAA": 949,
"GCGAT": 950,
"GCGAC": 951,
"GCGAG": 952,
"GCGTA": 953,
"GCGTT": 954,
"GCGTC": 955,
"GCGTG": 956,
"GCGCA": 957,
"GCGCT": 958,
"GCGCC": 959,
"GCGCG": 960,
"GCGGA": 961,
"GCGGT": 962,
"GCGGC": 963,
"GCGGG": 964,
"GGAAA": 965,
"GGAAT": 966,
"GGAAC": 967,
"GGAAG": 968,
"GGATA": 969,
"GGATT": 970,
"GGATC": 971,
"GGATG": 972,
"GGACA": 973,
"GGACT": 974,
"GGACC": 975,
"GGACG": 976,
"GGAGA": 977,
"GGAGT": 978,
"GGAGC": 979,
"GGAGG": 980,
"GGTAA": 981,
"GGTAT": 982,
"GGTAC": 983,
"GGTAG": 984,
"GGTTA": 985,
"GGTTT": 986,
"GGTTC": 987,
"GGTTG": 988,
"GGTCA": 989,
"GGTCT": 990,
"GGTCC": 991,
"GGTCG": 992,
"GGTGA": 993,
"GGTGT": 994,
"GGTGC": 995,
"GGTGG": 996,
"GGCAA": 997,
"GGCAT": 998,
"GGCAC": 999,
"GGCAG": 1000,
"GGCTA": 1001,
"GGCTT": 1002,
"GGCTC": 1003,
"GGCTG": 1004,
"GGCCA": 1005,
"GGCCT": 1006,
"GGCCC": 1007,
"GGCCG": 1008,
"GGCGA": 1009,
"GGCGT": 1010,
"GGCGC": 1011,
"GGCGG": 1012,
"GGGAA": 1013,
"GGGAT": 1014,
"GGGAC": 1015,
"GGGAG": 1016,
"GGGTA": 1017,
"GGGTT": 1018,
"GGGTC": 1019,
"GGGTG": 1020,
"GGGCA": 1021,
"GGGCT": 1022,
"GGGCC": 1023,
"GGGCG": 1024,
"GGGGA": 1025,
"GGGGT": 1026,
"GGGGC": 1027,
"GGGGG": 1028
}
}
}