Upload vocab.txt
c296157
|
[PAD] |
|
[UNK] |
|
[CLS] |
|
[SEP] |
|
[MASK] |
|
AAAAA |
|
AAAAT |
|
AAAAC |
|
AAAAG |
|
AAATA |
|
AAATT |
|
AAATC |
|
AAATG |
|
AAACA |
|
AAACT |
|
AAACC |
|
AAACG |
|
AAAGA |
|
AAAGT |
|
AAAGC |
|
AAAGG |
|
AATAA |
|
AATAT |
|
AATAC |
|
AATAG |
|
AATTA |
|
AATTT |
|
AATTC |
|
AATTG |
|
AATCA |
|
AATCT |
|
AATCC |
|
AATCG |
|
AATGA |
|
AATGT |
|
AATGC |
|
AATGG |
|
AACAA |
|
AACAT |
|
AACAC |
|
AACAG |
|
AACTA |
|
AACTT |
|
AACTC |
|
AACTG |
|
AACCA |
|
AACCT |
|
AACCC |
|
AACCG |
|
AACGA |
|
AACGT |
|
AACGC |
|
AACGG |
|
AAGAA |
|
AAGAT |
|
AAGAC |
|
AAGAG |
|
AAGTA |
|
AAGTT |
|
AAGTC |
|
AAGTG |
|
AAGCA |
|
AAGCT |
|
AAGCC |
|
AAGCG |
|
AAGGA |
|
AAGGT |
|
AAGGC |
|
AAGGG |
|
ATAAA |
|
ATAAT |
|
ATAAC |
|
ATAAG |
|
ATATA |
|
ATATT |
|
ATATC |
|
ATATG |
|
ATACA |
|
ATACT |
|
ATACC |
|
ATACG |
|
ATAGA |
|
ATAGT |
|
ATAGC |
|
ATAGG |
|
ATTAA |
|
ATTAT |
|
ATTAC |
|
ATTAG |
|
ATTTA |
|
ATTTT |
|
ATTTC |
|
ATTTG |
|
ATTCA |
|
ATTCT |
|
ATTCC |
|
ATTCG |
|
ATTGA |
|
ATTGT |
|
ATTGC |
|
ATTGG |
|
ATCAA |
|
ATCAT |
|
ATCAC |
|
ATCAG |
|
ATCTA |
|
ATCTT |
|
ATCTC |
|
ATCTG |
|
ATCCA |
|
ATCCT |
|
ATCCC |
|
ATCCG |
|
ATCGA |
|
ATCGT |
|
ATCGC |
|
ATCGG |
|
ATGAA |
|
ATGAT |
|
ATGAC |
|
ATGAG |
|
ATGTA |
|
ATGTT |
|
ATGTC |
|
ATGTG |
|
ATGCA |
|
ATGCT |
|
ATGCC |
|
ATGCG |
|
ATGGA |
|
ATGGT |
|
ATGGC |
|
ATGGG |
|
ACAAA |
|
ACAAT |
|
ACAAC |
|
ACAAG |
|
ACATA |
|
ACATT |
|
ACATC |
|
ACATG |
|
ACACA |
|
ACACT |
|
ACACC |
|
ACACG |
|
ACAGA |
|
ACAGT |
|
ACAGC |
|
ACAGG |
|
ACTAA |
|
ACTAT |
|
ACTAC |
|
ACTAG |
|
ACTTA |
|
ACTTT |
|
ACTTC |
|
ACTTG |
|
ACTCA |
|
ACTCT |
|
ACTCC |
|
ACTCG |
|
ACTGA |
|
ACTGT |
|
ACTGC |
|
ACTGG |
|
ACCAA |
|
ACCAT |
|
ACCAC |
|
ACCAG |
|
ACCTA |
|
ACCTT |
|
ACCTC |
|
ACCTG |
|
ACCCA |
|
ACCCT |
|
ACCCC |
|
ACCCG |
|
ACCGA |
|
ACCGT |
|
ACCGC |
|
ACCGG |
|
ACGAA |
|
ACGAT |
|
ACGAC |
|
ACGAG |
|
ACGTA |
|
ACGTT |
|
ACGTC |
|
ACGTG |
|
ACGCA |
|
ACGCT |
|
ACGCC |
|
ACGCG |
|
ACGGA |
|
ACGGT |
|
ACGGC |
|
ACGGG |
|
AGAAA |
|
AGAAT |
|
AGAAC |
|
AGAAG |
|
AGATA |
|
AGATT |
|
AGATC |
|
AGATG |
|
AGACA |
|
AGACT |
|
AGACC |
|
AGACG |
|
AGAGA |
|
AGAGT |
|
AGAGC |
|
AGAGG |
|
AGTAA |
|
AGTAT |
|
AGTAC |
|
AGTAG |
|
AGTTA |
|
AGTTT |
|
AGTTC |
|
AGTTG |
|
AGTCA |
|
AGTCT |
|
AGTCC |
|
AGTCG |
|
AGTGA |
|
AGTGT |
|
AGTGC |
|
AGTGG |
|
AGCAA |
|
AGCAT |
|
AGCAC |
|
AGCAG |
|
AGCTA |
|
AGCTT |
|
AGCTC |
|
AGCTG |
|
AGCCA |
|
AGCCT |
|
AGCCC |
|
AGCCG |
|
AGCGA |
|
AGCGT |
|
AGCGC |
|
AGCGG |
|
AGGAA |
|
AGGAT |
|
AGGAC |
|
AGGAG |
|
AGGTA |
|
AGGTT |
|
AGGTC |
|
AGGTG |
|
AGGCA |
|
AGGCT |
|
AGGCC |
|
AGGCG |
|
AGGGA |
|
AGGGT |
|
AGGGC |
|
AGGGG |
|
TAAAA |
|
TAAAT |
|
TAAAC |
|
TAAAG |
|
TAATA |
|
TAATT |
|
TAATC |
|
TAATG |
|
TAACA |
|
TAACT |
|
TAACC |
|
TAACG |
|
TAAGA |
|
TAAGT |
|
TAAGC |
|
TAAGG |
|
TATAA |
|
TATAT |
|
TATAC |
|
TATAG |
|
TATTA |
|
TATTT |
|
TATTC |
|
TATTG |
|
TATCA |
|
TATCT |
|
TATCC |
|
TATCG |
|
TATGA |
|
TATGT |
|
TATGC |
|
TATGG |
|
TACAA |
|
TACAT |
|
TACAC |
|
TACAG |
|
TACTA |
|
TACTT |
|
TACTC |
|
TACTG |
|
TACCA |
|
TACCT |
|
TACCC |
|
TACCG |
|
TACGA |
|
TACGT |
|
TACGC |
|
TACGG |
|
TAGAA |
|
TAGAT |
|
TAGAC |
|
TAGAG |
|
TAGTA |
|
TAGTT |
|
TAGTC |
|
TAGTG |
|
TAGCA |
|
TAGCT |
|
TAGCC |
|
TAGCG |
|
TAGGA |
|
TAGGT |
|
TAGGC |
|
TAGGG |
|
TTAAA |
|
TTAAT |
|
TTAAC |
|
TTAAG |
|
TTATA |
|
TTATT |
|
TTATC |
|
TTATG |
|
TTACA |
|
TTACT |
|
TTACC |
|
TTACG |
|
TTAGA |
|
TTAGT |
|
TTAGC |
|
TTAGG |
|
TTTAA |
|
TTTAT |
|
TTTAC |
|
TTTAG |
|
TTTTA |
|
TTTTT |
|
TTTTC |
|
TTTTG |
|
TTTCA |
|
TTTCT |
|
TTTCC |
|
TTTCG |
|
TTTGA |
|
TTTGT |
|
TTTGC |
|
TTTGG |
|
TTCAA |
|
TTCAT |
|
TTCAC |
|
TTCAG |
|
TTCTA |
|
TTCTT |
|
TTCTC |
|
TTCTG |
|
TTCCA |
|
TTCCT |
|
TTCCC |
|
TTCCG |
|
TTCGA |
|
TTCGT |
|
TTCGC |
|
TTCGG |
|
TTGAA |
|
TTGAT |
|
TTGAC |
|
TTGAG |
|
TTGTA |
|
TTGTT |
|
TTGTC |
|
TTGTG |
|
TTGCA |
|
TTGCT |
|
TTGCC |
|
TTGCG |
|
TTGGA |
|
TTGGT |
|
TTGGC |
|
TTGGG |
|
TCAAA |
|
TCAAT |
|
TCAAC |
|
TCAAG |
|
TCATA |
|
TCATT |
|
TCATC |
|
TCATG |
|
TCACA |
|
TCACT |
|
TCACC |
|
TCACG |
|
TCAGA |
|
TCAGT |
|
TCAGC |
|
TCAGG |
|
TCTAA |
|
TCTAT |
|
TCTAC |
|
TCTAG |
|
TCTTA |
|
TCTTT |
|
TCTTC |
|
TCTTG |
|
TCTCA |
|
TCTCT |
|
TCTCC |
|
TCTCG |
|
TCTGA |
|
TCTGT |
|
TCTGC |
|
TCTGG |
|
TCCAA |
|
TCCAT |
|
TCCAC |
|
TCCAG |
|
TCCTA |
|
TCCTT |
|
TCCTC |
|
TCCTG |
|
TCCCA |
|
TCCCT |
|
TCCCC |
|
TCCCG |
|
TCCGA |
|
TCCGT |
|
TCCGC |
|
TCCGG |
|
TCGAA |
|
TCGAT |
|
TCGAC |
|
TCGAG |
|
TCGTA |
|
TCGTT |
|
TCGTC |
|
TCGTG |
|
TCGCA |
|
TCGCT |
|
TCGCC |
|
TCGCG |
|
TCGGA |
|
TCGGT |
|
TCGGC |
|
TCGGG |
|
TGAAA |
|
TGAAT |
|
TGAAC |
|
TGAAG |
|
TGATA |
|
TGATT |
|
TGATC |
|
TGATG |
|
TGACA |
|
TGACT |
|
TGACC |
|
TGACG |
|
TGAGA |
|
TGAGT |
|
TGAGC |
|
TGAGG |
|
TGTAA |
|
TGTAT |
|
TGTAC |
|
TGTAG |
|
TGTTA |
|
TGTTT |
|
TGTTC |
|
TGTTG |
|
TGTCA |
|
TGTCT |
|
TGTCC |
|
TGTCG |
|
TGTGA |
|
TGTGT |
|
TGTGC |
|
TGTGG |
|
TGCAA |
|
TGCAT |
|
TGCAC |
|
TGCAG |
|
TGCTA |
|
TGCTT |
|
TGCTC |
|
TGCTG |
|
TGCCA |
|
TGCCT |
|
TGCCC |
|
TGCCG |
|
TGCGA |
|
TGCGT |
|
TGCGC |
|
TGCGG |
|
TGGAA |
|
TGGAT |
|
TGGAC |
|
TGGAG |
|
TGGTA |
|
TGGTT |
|
TGGTC |
|
TGGTG |
|
TGGCA |
|
TGGCT |
|
TGGCC |
|
TGGCG |
|
TGGGA |
|
TGGGT |
|
TGGGC |
|
TGGGG |
|
CAAAA |
|
CAAAT |
|
CAAAC |
|
CAAAG |
|
CAATA |
|
CAATT |
|
CAATC |
|
CAATG |
|
CAACA |
|
CAACT |
|
CAACC |
|
CAACG |
|
CAAGA |
|
CAAGT |
|
CAAGC |
|
CAAGG |
|
CATAA |
|
CATAT |
|
CATAC |
|
CATAG |
|
CATTA |
|
CATTT |
|
CATTC |
|
CATTG |
|
CATCA |
|
CATCT |
|
CATCC |
|
CATCG |
|
CATGA |
|
CATGT |
|
CATGC |
|
CATGG |
|
CACAA |
|
CACAT |
|
CACAC |
|
CACAG |
|
CACTA |
|
CACTT |
|
CACTC |
|
CACTG |
|
CACCA |
|
CACCT |
|
CACCC |
|
CACCG |
|
CACGA |
|
CACGT |
|
CACGC |
|
CACGG |
|
CAGAA |
|
CAGAT |
|
CAGAC |
|
CAGAG |
|
CAGTA |
|
CAGTT |
|
CAGTC |
|
CAGTG |
|
CAGCA |
|
CAGCT |
|
CAGCC |
|
CAGCG |
|
CAGGA |
|
CAGGT |
|
CAGGC |
|
CAGGG |
|
CTAAA |
|
CTAAT |
|
CTAAC |
|
CTAAG |
|
CTATA |
|
CTATT |
|
CTATC |
|
CTATG |
|
CTACA |
|
CTACT |
|
CTACC |
|
CTACG |
|
CTAGA |
|
CTAGT |
|
CTAGC |
|
CTAGG |
|
CTTAA |
|
CTTAT |
|
CTTAC |
|
CTTAG |
|
CTTTA |
|
CTTTT |
|
CTTTC |
|
CTTTG |
|
CTTCA |
|
CTTCT |
|
CTTCC |
|
CTTCG |
|
CTTGA |
|
CTTGT |
|
CTTGC |
|
CTTGG |
|
CTCAA |
|
CTCAT |
|
CTCAC |
|
CTCAG |
|
CTCTA |
|
CTCTT |
|
CTCTC |
|
CTCTG |
|
CTCCA |
|
CTCCT |
|
CTCCC |
|
CTCCG |
|
CTCGA |
|
CTCGT |
|
CTCGC |
|
CTCGG |
|
CTGAA |
|
CTGAT |
|
CTGAC |
|
CTGAG |
|
CTGTA |
|
CTGTT |
|
CTGTC |
|
CTGTG |
|
CTGCA |
|
CTGCT |
|
CTGCC |
|
CTGCG |
|
CTGGA |
|
CTGGT |
|
CTGGC |
|
CTGGG |
|
CCAAA |
|
CCAAT |
|
CCAAC |
|
CCAAG |
|
CCATA |
|
CCATT |
|
CCATC |
|
CCATG |
|
CCACA |
|
CCACT |
|
CCACC |
|
CCACG |
|
CCAGA |
|
CCAGT |
|
CCAGC |
|
CCAGG |
|
CCTAA |
|
CCTAT |
|
CCTAC |
|
CCTAG |
|
CCTTA |
|
CCTTT |
|
CCTTC |
|
CCTTG |
|
CCTCA |
|
CCTCT |
|
CCTCC |
|
CCTCG |
|
CCTGA |
|
CCTGT |
|
CCTGC |
|
CCTGG |
|
CCCAA |
|
CCCAT |
|
CCCAC |
|
CCCAG |
|
CCCTA |
|
CCCTT |
|
CCCTC |
|
CCCTG |
|
CCCCA |
|
CCCCT |
|
CCCCC |
|
CCCCG |
|
CCCGA |
|
CCCGT |
|
CCCGC |
|
CCCGG |
|
CCGAA |
|
CCGAT |
|
CCGAC |
|
CCGAG |
|
CCGTA |
|
CCGTT |
|
CCGTC |
|
CCGTG |
|
CCGCA |
|
CCGCT |
|
CCGCC |
|
CCGCG |
|
CCGGA |
|
CCGGT |
|
CCGGC |
|
CCGGG |
|
CGAAA |
|
CGAAT |
|
CGAAC |
|
CGAAG |
|
CGATA |
|
CGATT |
|
CGATC |
|
CGATG |
|
CGACA |
|
CGACT |
|
CGACC |
|
CGACG |
|
CGAGA |
|
CGAGT |
|
CGAGC |
|
CGAGG |
|
CGTAA |
|
CGTAT |
|
CGTAC |
|
CGTAG |
|
CGTTA |
|
CGTTT |
|
CGTTC |
|
CGTTG |
|
CGTCA |
|
CGTCT |
|
CGTCC |
|
CGTCG |
|
CGTGA |
|
CGTGT |
|
CGTGC |
|
CGTGG |
|
CGCAA |
|
CGCAT |
|
CGCAC |
|
CGCAG |
|
CGCTA |
|
CGCTT |
|
CGCTC |
|
CGCTG |
|
CGCCA |
|
CGCCT |
|
CGCCC |
|
CGCCG |
|
CGCGA |
|
CGCGT |
|
CGCGC |
|
CGCGG |
|
CGGAA |
|
CGGAT |
|
CGGAC |
|
CGGAG |
|
CGGTA |
|
CGGTT |
|
CGGTC |
|
CGGTG |
|
CGGCA |
|
CGGCT |
|
CGGCC |
|
CGGCG |
|
CGGGA |
|
CGGGT |
|
CGGGC |
|
CGGGG |
|
GAAAA |
|
GAAAT |
|
GAAAC |
|
GAAAG |
|
GAATA |
|
GAATT |
|
GAATC |
|
GAATG |
|
GAACA |
|
GAACT |
|
GAACC |
|
GAACG |
|
GAAGA |
|
GAAGT |
|
GAAGC |
|
GAAGG |
|
GATAA |
|
GATAT |
|
GATAC |
|
GATAG |
|
GATTA |
|
GATTT |
|
GATTC |
|
GATTG |
|
GATCA |
|
GATCT |
|
GATCC |
|
GATCG |
|
GATGA |
|
GATGT |
|
GATGC |
|
GATGG |
|
GACAA |
|
GACAT |
|
GACAC |
|
GACAG |
|
GACTA |
|
GACTT |
|
GACTC |
|
GACTG |
|
GACCA |
|
GACCT |
|
GACCC |
|
GACCG |
|
GACGA |
|
GACGT |
|
GACGC |
|
GACGG |
|
GAGAA |
|
GAGAT |
|
GAGAC |
|
GAGAG |
|
GAGTA |
|
GAGTT |
|
GAGTC |
|
GAGTG |
|
GAGCA |
|
GAGCT |
|
GAGCC |
|
GAGCG |
|
GAGGA |
|
GAGGT |
|
GAGGC |
|
GAGGG |
|
GTAAA |
|
GTAAT |
|
GTAAC |
|
GTAAG |
|
GTATA |
|
GTATT |
|
GTATC |
|
GTATG |
|
GTACA |
|
GTACT |
|
GTACC |
|
GTACG |
|
GTAGA |
|
GTAGT |
|
GTAGC |
|
GTAGG |
|
GTTAA |
|
GTTAT |
|
GTTAC |
|
GTTAG |
|
GTTTA |
|
GTTTT |
|
GTTTC |
|
GTTTG |
|
GTTCA |
|
GTTCT |
|
GTTCC |
|
GTTCG |
|
GTTGA |
|
GTTGT |
|
GTTGC |
|
GTTGG |
|
GTCAA |
|
GTCAT |
|
GTCAC |
|
GTCAG |
|
GTCTA |
|
GTCTT |
|
GTCTC |
|
GTCTG |
|
GTCCA |
|
GTCCT |
|
GTCCC |
|
GTCCG |
|
GTCGA |
|
GTCGT |
|
GTCGC |
|
GTCGG |
|
GTGAA |
|
GTGAT |
|
GTGAC |
|
GTGAG |
|
GTGTA |
|
GTGTT |
|
GTGTC |
|
GTGTG |
|
GTGCA |
|
GTGCT |
|
GTGCC |
|
GTGCG |
|
GTGGA |
|
GTGGT |
|
GTGGC |
|
GTGGG |
|
GCAAA |
|
GCAAT |
|
GCAAC |
|
GCAAG |
|
GCATA |
|
GCATT |
|
GCATC |
|
GCATG |
|
GCACA |
|
GCACT |
|
GCACC |
|
GCACG |
|
GCAGA |
|
GCAGT |
|
GCAGC |
|
GCAGG |
|
GCTAA |
|
GCTAT |
|
GCTAC |
|
GCTAG |
|
GCTTA |
|
GCTTT |
|
GCTTC |
|
GCTTG |
|
GCTCA |
|
GCTCT |
|
GCTCC |
|
GCTCG |
|
GCTGA |
|
GCTGT |
|
GCTGC |
|
GCTGG |
|
GCCAA |
|
GCCAT |
|
GCCAC |
|
GCCAG |
|
GCCTA |
|
GCCTT |
|
GCCTC |
|
GCCTG |
|
GCCCA |
|
GCCCT |
|
GCCCC |
|
GCCCG |
|
GCCGA |
|
GCCGT |
|
GCCGC |
|
GCCGG |
|
GCGAA |
|
GCGAT |
|
GCGAC |
|
GCGAG |
|
GCGTA |
|
GCGTT |
|
GCGTC |
|
GCGTG |
|
GCGCA |
|
GCGCT |
|
GCGCC |
|
GCGCG |
|
GCGGA |
|
GCGGT |
|
GCGGC |
|
GCGGG |
|
GGAAA |
|
GGAAT |
|
GGAAC |
|
GGAAG |
|
GGATA |
|
GGATT |
|
GGATC |
|
GGATG |
|
GGACA |
|
GGACT |
|
GGACC |
|
GGACG |
|
GGAGA |
|
GGAGT |
|
GGAGC |
|
GGAGG |
|
GGTAA |
|
GGTAT |
|
GGTAC |
|
GGTAG |
|
GGTTA |
|
GGTTT |
|
GGTTC |
|
GGTTG |
|
GGTCA |
|
GGTCT |
|
GGTCC |
|
GGTCG |
|
GGTGA |
|
GGTGT |
|
GGTGC |
|
GGTGG |
|
GGCAA |
|
GGCAT |
|
GGCAC |
|
GGCAG |
|
GGCTA |
|
GGCTT |
|
GGCTC |
|
GGCTG |
|
GGCCA |
|
GGCCT |
|
GGCCC |
|
GGCCG |
|
GGCGA |
|
GGCGT |
|
GGCGC |
|
GGCGG |
|
GGGAA |
|
GGGAT |
|
GGGAC |
|
GGGAG |
|
GGGTA |
|
GGGTT |
|
GGGTC |
|
GGGTG |
|
GGGCA |
|
GGGCT |
|
GGGCC |
|
GGGCG |
|
GGGGA |
|
GGGGT |
|
GGGGC |
|
GGGGG |
|
|
