Upload vocab.txt
6b22311
verified
|
[PAD] |
|
[UNK] |
|
[CLS] |
|
[SEP] |
|
[MASK] |
|
A |
|
C |
|
G |
|
T |
|
TT |
|
AA |
|
TG |
|
AG |
|
CC |
|
TC |
|
AC |
|
GG |
|
ATT |
|
AT |
|
ATG |
|
GC |
|
TAA |
|
TCC |
|
ACC |
|
AAAA |
|
AGG |
|
ATC |
|
AGC |
|
TTC |
|
AAG |
|
TTTT |
|
TGC |
|
TGG |
|
AAC |
|
TTG |
|
TAG |
|
TAC |
|
CCC |
|
TATT |
|
TGGG |
|
TAT |
|
AGAA |
|
AGGG |
|
TTTC |
|
AGGC |
|
AGCC |
|
ATAA |
|
TGTG |
|
TTGG |
|
ATTC |
|
AAGG |
|
ACAC |
|
TCCC |
|
TCTC |
|
TATG |
|
TTTG |
|
TTCC |
|
AGTG |
|
ATGG |
|
AGAC |
|
AAAC |
|
ACCC |
|
TGCC |
|
ATTG |
|
ATCC |
|
AGAG |
|
ATGC |
|
ATAC |
|
TCTG |
|
TTAA |
|
TCAC |
|
TGAA |
|
TGGC |
|
TTGC |
|
TAAG |
|
TATC |
|
TAAC |
|
AAAG |
|
TTAC |
|
AAGC |
|
GGG |
|
TAGC |
|
GGC |
|
ATAT |
|
TACC |
|
AACC |
|
AATG |
|
TAGG |
|
GCC |
|
ATATT |
|
AGTC |
|
TTTTC |
|
AAAAC |
|
TGAC |
|
TTTAA |
|
AAAAG |
|
AATC |
|
TGTC |
|
TTATT |
|
ATAG |
|
TGAG |
|
TTTTG |
|
AAATT |
|
AATT |
|
AATAA |
|
TTTCC |
|
ACAG |
|
TCAG |
|
AAATG |
|
TGGGC |
|
ACTC |
|
AGGCC |
|
TTAG |
|
ACTG |
|
ACG |
|
ATATG |
|
TGGCC |
|
ATTTC |
|
ACAA |
|
ATCTC |
|
TATTC |
|
TGTAA |
|
ACTT |
|
ATGCC |
|
TAAAA |
|
AAAAAAAA |
|
ATTCC |
|
TTTAG |
|
TCCCC |
|
TTTGC |
|
TTCCC |
|
TGGGG |
|
TTCTC |
|
ATAAAA |
|
AGAAG |
|
TTTTTTTT |
|
ACCCC |
|
AGGGC |
|
ACCTC |
|
AGATG |
|
ATTAC |
|
AAGCC |
|
GGCC |
|
AGGAG |
|
TCAA |
|
ATTGC |
|
TATTG |
|
ATAAC |
|
ATATC |
|
TTTAC |
|
ATGGC |
|
AAGGC |
|
ACCAC |
|
GTG |
|
ATCCC |
|
AGAAC |
|
ATTTT |
|
TTGCC |
|
AAATC |
|
ATAAG |
|
TTGGC |
|
TGGAG |
|
ATGGG |
|
AAAGC |
|
AGGGG |
|
ATCAC |
|
ATTTG |
|
AATTC |
|
TGCAC |
|
TTTGG |
|
TCG |
|
AGAGC |
|
AAAGG |
|
GGGC |
|
TTGGG |
|
AGAAAA |
|
TATCC |
|
TCTCC |
|
ATAGC |
|
TGAGG |
|
TTTATT |
|
AGTAA |
|
AGAGG |
|
TCTTC |
|
ACATT |
|
TCCTG |
|
AGCCC |
|
TATGC |
|
TTAAAA |
|
AGATT |
|
TTAAC |
|
GGGG |
|
AAGAC |
|
TCATT |
|
TTCTG |
|
AGACC |
|
AAGGG |
|
ATACC |
|
TTTAT |
|
AAGTG |
|
TTATG |
|
AAGAA |
|
TAGCC |
|
TTCAC |
|
AGGTG |
|
TTGAA |
|
ATCTG |
|
AGCAC |
|
TGCTG |
|
AAACC |
|
ATGTG |
|
TTTTCC |
|
AGTTC |
|
TCCTC |
|
TATGG |
|
AATAC |
|
AGTGG |
|
TAGGC |
|
AGCTC |
|
ATAGG |
|
TTATC |
|
TTAAG |
|
TACCC |
|
TTTTTG |
|
AACAC |
|
TGCTC |
|
AGATC |
|
TCCCAGC |
|
AGCTG |
|
AATAG |
|
TCTTG |
|
AGTGGC |
|
ATTGG |
|
TACTC |
|
TAAAC |
|
AATGG |
|
AGGTC |
|
AGGAC |
|
TTGTG |
|
TATAC |
|
ATTTTC |
|
ATATAA |
|
AGGCTG |
|
ATTTAA |
|
AGTT |
|
AGTAG |
|
ATGAC |
|
AATGC |
|
TCCAC |
|
CCCC |
|
ATGTC |
|
AACTC |
|
TTTTTC |
|
TAAGC |
|
AAGTC |
|
TGGTG |
|
TATAA |
|
AGTGC |
|
TAAGG |
|
ACCTG |
|
TTAGC |
|
AAATAA |
|
TGCCTC |
|
AATCC |
|
TTGGCC |
|
TAGGG |
|
TGGAC |
|
TTGTC |
|
AACCC |
|
TTACC |
|
TAACC |
|
AATTTT |
|
AAAGAA |
|
ATTATT |
|
AGCG |
|
AAAAAC |
|
TAATG |
|
TTGAC |
|
AGTCC |
|
AACTG |
|
AGTTG |
|
AATTG |
|
TCTGC |
|
TTAGG |
|
TACAC |
|
AGAAGG |
|
ATATTC |
|
AAAACC |
|
AAAAGC |
|
TGCCC |
|
ACTGC |
|
AGAAGC |
|
TAATAA |
|
AATATT |
|
ACCATG |
|
TGGTC |
|
TTTTGC |
|
AACG |
|
TACTG |
|
ACACACAC |
|
ATTTTG |
|
TCCG |
|
TGCG |
|
AAAATG |
|
ACATG |
|
TCAGC |
|
ATCG |
|
AGTAC |
|
TTTTGG |
|
AATAT |
|
AGAGAA |
|
TTCG |
|
TCCAGCC |
|
ATATAC |
|
TCACC |
|
AAAAGG |
|
TGTGTGTG |
|
TCATC |
|
TGCTGGG |
|
TGAAG |
|
TGTAG |
|
TGTGG |
|
AAAAATT |
|
ACTTC |
|
TTCCCC |
|
ATAGAA |
|
TTGCCC |
|
AGGAGG |
|
TTTCCC |
|
TATATT |
|
ACCG |
|
ACTAC |
|
TCACTGC |
|
GCG |
|
TTTGTG |
|
ACAGC |
|
TCATG |
|
AGTTTT |
|
AGGAA |
|
TTTATG |
|
ATATTG |
|
TGATG |
|
TCTAA |
|
TGTGC |
|
AGGAAG |
|
TTTGGG |
|
TGTTC |
|
AGCCCC |
|
AGTTTC |
|
AGGCTGG |
|
TTTGCC |
|
ATTTCC |
|
ATACAC |
|
AAAATAA |
|
TAGAC |
|
AGGAGAA |
|
TGAGC |
|
TGGAA |
|
TTTTTAA |
|
AGCCTCCC |
|
ATGAA |
|
TTTAAG |
|
TCTGG |
|
TTTATC |
|
TTATAA |
|
TGATT |
|
AACAA |
|
TAGCTGGG |
|
TCAAG |
|
AAAAAA |
|
ACTTTGGG |
|
TATTCC |
|
TCAGG |
|
AACAG |
|
TTCTTC |
|
TGTGGC |
|
ATATGC |
|
ATTACAGGC |
|
AGGGGC |
|
AGGGCC |
|
TTATTC |
|
ATATCC |
|
TGTAATCCCAGC |
|
TACG |
|
AGAAAC |
|
TGTCC |
|
AGATGG |
|
TGTGCC |
|
TTTCTC |
|
TGAAC |
|
AGTCTC |
|
TGTTG |
|
ATTTTTT |
|
AAGAAG |
|
TGGGGC |
|
AGCAGC |
|
GCCC |
|
TTTGGC |
|
AGGCTGAGGC |
|
TGGGCC |
|
TTCTCC |
|
TAGAA |
|
TGGAGTGC |
|
ATTAA |
|
AGTGCC |
|
TGTCTC |
|
ATATGG |
|
ACATC |
|
TGGGGG |
|
TGACC |
|
ACTCC |
|
TAAAAC |
|
AGATAA |
|
TAATTTT |
|
TCAAC |
|
TCTAC |
|
TCTAG |
|
GAG |
|
TAAATG |
|
AGCAA |
|
TATATG |
|
ATATATAT |
|
ATTTGC |
|
TCCTCC |
|
CCCAC |
|
ATTTATT |
|
TCTGCC |
|
ATGGCC |
|
TCGC |
|
AGTATT |
|
AGAACC |
|
TTAAAC |
|
AAATTC |
|
AGAGAC |
|
ATTTAC |
|
ATTGCC |
|
AACAAC |
|
TTTAAC |
|
ACGG |
|
AAGAAAA |
|
TCTGGC |
|
ATTCTCC |
|
AGGTGG |
|
TGCTGC |
|
TTCAAG |
|
AGAGGG |
|
ACACC |
|
TCTTTT |
|
AGAGGC |
|
ATCACC |
|
TAAATT |
|
AAGGCC |
|
TTGCAGTG |
|
TGTAC |
|
AATTTC |
|
ATCCCC |
|
ACAAG |
|
ACAGG |
|
ACAAC |
|
TGCCCC |
|
AGATTC |
|
TTAGAA |
|
TTGGGG |
|
AGACAC |
|
TGGAAG |
|
ACCTCC |
|
ATGGGG |
|
AGCCTCC |
|
TTATTG |
|
TAAAAG |
|
ATCTTC |
|
ATCTCC |
|
TGAAGC |
|
TAATC |
|
AAATGC |
|
TTGTTG |
|
ATTCCC |
|
TACTAAAA |
|
ATAGTG |
|
AAATAC |
|
TTGGGC |
|
TAGAGAC |
|
TGTTTT |
|
TTCTGC |
|
TGGCCC |
|
TCTGTC |
|
AGCTCC |
|
AACTCC |
|
TTAGCC |
|
AAAGTGCTGGG |
|
ATAGAC |
|
TATTTTTAG |
|
ACTTG |
|
ACCACC |
|
AAACAC |
|
GTGG |
|
ATTTAG |
|
AGGAGC |
|
AGGCTGGAGTGC |
|
ATACCC |
|
ATGTAA |
|
ACGC |
|
AGTAT |
|
TTTACC |
|
ACTAA |
|
AGGCCC |
|
AAGGGG |
|
TCTCG |
|
ATGAAG |
|
AAAGAC |
|
TGAAAA |
|
AAGGGC |
|
ATAGGC |
|
AGAGTG |
|
AGCTGC |
|
ATGTTC |
|
TATTTC |
|
TGATC |
|
AGTTTG |
|
AGCTAA |
|
AGAGCC |
|
TGCTTC |
|
ATCATC |
|
AACATGG |
|
AGCTTC |
|
AAGAAC |
|
TTTTTTG |
|
AGGGGG |
|
ATAAGC |
|
TAAGCC |
|
ACTGG |
|
ACAAAA |
|
ATCATT |
|
TCTTTC |
|
ATGATG |
|
TGCAA |
|
AGGTTC |
|
AACATT |
|
ATGGGC |
|
ATAGAG |
|
AAATGG |
|
AGTTCC |
|
TTTAGC |
|
AACTTC |
|
AGCAAG |
|
ATAAAAC |
|
AAAATC |
|
AGCCAC |
|
AGGAAC |
|
TTAACC |
|
TATTTATT |
|
TTTCTG |
|
ATAAGG |
|
AGCCACC |
|
AGATGC |
|
TTAAGC |
|
TTGTAA |
|
AGTGTG |
|
AACCCC |
|
TTCATT |
|
ATCATG |
|
AATGAA |
|
AGGTGC |
|
AAAAAAAAAAAAAAAA |
|
AGGATG |
|
AGCCG |
|
TGGTGG |
|
AGTGGG |
|
TGCACTCCAGCC |
|
TATTGC |
|
TAGTC |
|
CCCG |
|
AAGTAA |
|
TAGTG |
|
TTTTTTTTTTTTTTTT |
|
AGCATT |
|
ATCTGC |
|
TCTCAC |
|
AAATTG |
|
TTTAGG |
|
AGACCC |
|
GGGCC |
|
TCCTTC |
|
ATAGGG |
|
AATATG |
|
TTATAC |
|
TAGAAG |
|
AAAGTG |
|
AAATCC |
|
TTCCTC |
|
TTTCAC |
|
AGTATG |
|
TACTAAAAATAC |
|
ATGTGC |
|
AGGAGGC |
|
TATATC |
|
TTCTAA |
|
TGAGGC |
|
ACACAC |
|
TCCCCC |
|
AACATC |
|
AAGCG |
|
AATGGC |
|
ACCCCC |
|
AGATAC |
|
ATAAAAG |
|
ATGATT |
|
TGGAGG |
|
AGTTAA |
|
|
|
|
