| { |
| "additional_special_tokens": [ |
| "<molecule_2d>", |
| "<molecule_3d>", |
| "<protein>", |
| "<|CNC[C@H]1Oc2ccccc2C(=O)N([C@H](C)CO)C[C@@H]1C|>", |
| "<|Nc1cc(=O)[nH]c(=O)n1Cc1ccccc1|>", |
| "<|O=C(NCc1ccccc1)c1ccccc1|>", |
| "<|O=C(Nc1ccccc1)c1ccccc1|>", |
| "<|O=C(c1ccccc1)N1CCNCC1|>", |
| "<|Cc1cc(=O)n(-c2ccccc2)n1C|>", |
| "<|O=C(c1ccccc1)N1CCCCC1|>", |
| "<|CC(=O)Nc1ccc(S(N)(=O)=O)cc1|>", |
| "<|CC(=O)Nc1ccc2c(c1)OCCO2|>", |
| "<|CCN(CC)S(=O)(=O)c1ccccc1|>", |
| "<|COc1ccc(N2CCNCC2)cc1|>", |
| "<|O=C(c1ccccc1)c1ccccc1|>", |
| "<|O=C(c1ccccc1)N1CCOCC1|>", |
| "<|O=C(Nc1ccccc1)c1ccco1|>", |
| "<|NC(=O)COC(=O)c1ccccc1|>", |
| "<|CCNS(=O)(=O)c1ccc(C)cc1|>", |
| "<|Cc1cc(=O)n(-c2ccccc2)n1|>", |
| "<|COc1cc(C)cc(OC)c1OC|>", |
| "<|c1ccc(Cc2ccccc2)cc1|>", |
| "<|CCNC(=O)c1cccc(OC)c1|>", |
| "<|COc1ccc(C(N)=O)cc1OC|>", |
| "<|C[C@H](CO)NC(=O)c1ccccc1|>", |
| "<|Cn1c(=O)c2ncnc2n(C)c1=O|>", |
| "<|CCOc1ccc(NC(C)=O)cc1|>", |
| "<|O=CCNS(=O)(=O)c1ccccc1|>", |
| "<|NC(=O)CNC(=O)c1ccccc1|>", |
| "<|NC(=O)c1ccnc2ccccc12|>", |
| "<|CCN1C(=O)c2ccccc2C1=O|>", |
| "<|NC(=O)C1COc2ccccc2O1|>", |
| "<|c1ccc(Oc2ccccc2)cc1|>", |
| "<|CCCCn1c(N)cc(=O)[nH]c1=O|>", |
| "<|c1ccc2nc3nccc3nc2c1|>", |
| "<|c1ccc(CN2CCNCC2)cc1|>", |
| "<|CCNC(=O)c1ccc(OC)cc1|>", |
| "<|CCNS(=O)(=O)c1ccccc1|>", |
| "<|O=CCNC(=O)c1ccccc1|>", |
| "<|Cc1ccn(-c2ccccc2)n1|>", |
| "<|COc1cccc(OC)c1OC|>", |
| "<|COc1ccc(NC(C)=O)cc1|>", |
| "<|CC(=O)NCCc1ccccc1|>", |
| "<|NC(=O)C1CCN([SH](=O)=O)CC1|>", |
| "<|ccc1cnc2ccccc2n1|>", |
| "<|NC(=O)c1cccc([N+](=O)[O-])c1|>", |
| "<|Cc1cc(=O)oc2ccccc12|>", |
| "<|CCN(C)C(=O)c1ccccc1|>", |
| "<|CCCNC(=O)c1ccccc1|>", |
| "<|COc1ccc2ccccc2c1|>", |
| "<|c1ccc(N2CCNCC2)cc1|>", |
| "<|COc1ccccc1NC(C)=O|>", |
| "<|CCNC(=O)c1ccc(C)cc1|>", |
| "<|CCOc1ccccc1OCC|>", |
| "<|c1ccc(-c2ccccc2)cc1|>", |
| "<|Cc1ccc2ccc(=O)oc2c1|>", |
| "<|O=c1nc(=O)c2ccccc2n1|>", |
| "<|CCNC(=O)c1ccc(Cl)cc1|>", |
| "<|CC1NC(=O)N(CC(N)=O)C1=O|>", |
| "<|Cn1c(=O)[nH]c(=O)c2ncnc21|>", |
| "<|O=CCOC(=O)c1ccccc1|>", |
| "<|Cc1nc(=O)c2ccccc2n1|>", |
| "<|CCNC(=O)c1ccccc1|>", |
| "<|O=c1ncnc2ccccc12|>", |
| "<|COc1ccc(C)cc1OC|>", |
| "<|O=c1ccc2ccccc2o1|>", |
| "<|COc1cccc(C(N)=O)c1|>", |
| "<|CC(=O)NCc1ccccc1|>", |
| "<|CCOC(=O)c1ccccc1|>", |
| "<|CCC(=O)Nc1ccccc1|>", |
| "<|O=C(CS)Nc1ccccc1|>", |
| "<|Cc1ccc(S(N)(=O)=O)cc1|>", |
| "<|c1ccc(-n2cccn2)cc1|>", |
| "<|COc1ccc(C(N)=O)cc1|>", |
| "<|NC(=O)COc1ccccc1|>", |
| "<|O=C(CO)Nc1ccccc1|>", |
| "<|O=c1ccoc2ccccc12|>", |
| "<|O=c1nccc2ccccc12|>", |
| "<|O=c1nncc2ccccc12|>", |
| "<|Cc1ccc2ccccc2n1|>", |
| "<|CCN(C)Cc1ccccc1|>", |
| "<|CC(=O)Nc1ccc(C)cc1|>", |
| "<|O=c1ccnc2ccccc12|>", |
| "<|O=c1cnc2cncnc2n1|>", |
| "<|Oc1ccc2ccccc2n1|>", |
| "<|COc1ccccc1C(N)=O|>", |
| "<|O=c1ccc2ccccc2n1|>", |
| "<|Cc1ccc2ncccc2c1|>", |
| "<|Oc1ccc2ccccc2c1|>", |
| "<|Oc1ncnc2ccccc12|>", |
| "<|Cc1cccc2ccccc12|>", |
| "<|Cn1cnnc1SCC(N)=O|>", |
| "<|Cc1sc2ncncc2c1C|>", |
| "<|COc1ccc(C)c(OC)c1|>", |
| "<|O=C1NC(=O)c2ccccc21|>", |
| "<|Cc1ccnc2ccccc12|>", |
| "<|O=C1COc2ccccc2N1|>", |
| "<|Cn1cnc(=O)c2ncnc21|>", |
| "<|O=CNCCc1ccccc1|>", |
| "<|COc1cccc(C)c1OC|>", |
| "<|CNS(=O)(=O)c1ccccc1|>", |
| "<|CC1NC(=O)N(CC=O)C1=O|>", |
| "<|Nc1ccc(S(N)(=O)=O)cc1|>", |
| "<|O=c1ccnc2ccccn12|>", |
| "<|O=CN1CCN([SH](=O)=O)CC1|>", |
| "<|CC(=O)Nc1ccccc1C|>", |
| "<|CCNC(=O)C1CCNCC1|>", |
| "<|OCC1OCC(O)C(O)C1O|>", |
| "<|FC(F)(F)c1cncc(Cl)c1|>", |
| "<|COc1ccc(OC)c(C)c1|>", |
| "<|CC(=O)Nc1ccc(F)cc1|>", |
| "<|Cc1nncc2nnc(C)c12|>", |
| "<|c1ccc(-c2cscn2)cc1|>", |
| "<|Cc1cnc2ccccc2c1|>", |
| "<|c1ccc(-c2nnco2)cc1|>", |
| "<|FC(F)(F)Oc1ccccc1|>", |
| "<|O=[SH](=O)NCc1ccccc1|>", |
| "<|O=c1cnc2ccccc2n1|>", |
| "<|NC(=O)CCc1ccccc1|>", |
| "<|CCOC(=O)C1CCNCC1|>", |
| "<|Cc1cc(C)n2ncnc2n1|>", |
| "<|CCNCCc1ccccc1|>", |
| "<|O=CCNC(=O)c1ccco1|>", |
| "<|COc1ccc(NC=O)cc1|>", |
| "<|COc1ccc2ncsc2c1|>", |
| "<|COc1ccc2[nH]ccc2c1|>", |
| "<|COc1ccc(C(=O)O)cc1|>", |
| "<|NCC(=O)Nc1ccccc1|>", |
| "<|Nc1ncnc2ccccc12|>", |
| "<|Oc1cccc2cccnc12|>", |
| "<|NS(=O)(=O)c1ccc(Cl)cc1|>", |
| "<|CC(=O)Nc1ccccc1|>", |
| "<|c1ccc2ncccc2c1|>", |
| "<|COc1ccccc1OC|>", |
| "<|FC(F)(F)c1ccccc1|>", |
| "<|c1ccc2ccccc2c1|>", |
| "<|c1ccc2ncncc2c1|>", |
| "<|NS(=O)(=O)c1ccccc1|>", |
| "<|Cc1ccc2c(c1)OCO2|>", |
| "<|COc1cccc(OC)c1|>", |
| "<|O=cccc1ccccc1|>", |
| "<|COC(=O)c1ccccc1|>", |
| "<|CNC(=O)c1ccccc1|>", |
| "<|c1ccc2cnncc2c1|>", |
| "<|c1ccc2nccnc2c1|>", |
| "<|NC(=O)CSc1ncnn1|>", |
| "<|CCNCc1ccccc1|>", |
| "<|COc1ccc(OC)cc1|>", |
| "<|Cc1ccc([SH](=O)=O)cc1|>", |
| "<|c1ccc2c(c1)OCCO2|>", |
| "<|Cc1cc2ccccc2[nH]1|>", |
| "<|c1ccc2occcc2c1|>", |
| "<|O=CNCc1ccccc1|>", |
| "<|CCNC(=O)c1ccco1|>", |
| "<|O=c1ncnc2sccc12|>", |
| "<|FC(F)Oc1ccccc1|>", |
| "<|COc1cc(C)ccc1O|>", |
| "<|NC(=O)c1ccccc1Cl|>", |
| "<|Cc1ccc(C(N)=O)cc1|>", |
| "<|C1C2CC3CC1CC(C2)C3|>", |
| "<|O=COCc1ccccc1|>", |
| "<|Cn1ccc2ccccc21|>", |
| "<|Cc1cc2ccccc2n1|>", |
| "<|NC(=O)Cc1ccccc1|>", |
| "<|NC(=O)c1ccccc1F|>", |
| "<|NC(=O)Nc1ccccc1|>", |
| "<|COc1cccc(C=O)c1|>", |
| "<|O=CCOc1ccccc1|>", |
| "<|O=c1ccnc2scnn12|>", |
| "<|Cc1ccc([N+](=O)[O-])cc1|>", |
| "<|NNC(=O)c1ccccc1|>", |
| "<|CCC(=O)N1CCNCC1|>", |
| "<|Cn1cnc2ccccc21|>", |
| "<|Cc1cccc([N+](=O)[O-])c1|>", |
| "<|Cc1ccn2ncnc2n1|>", |
| "<|CCCCc1ccccc1|>", |
| "<|Cc1coc2ccccc12|>", |
| "<|Cn1ccc(=O)n(C)c1=O|>", |
| "<|CN1CCN([SH](=O)=O)CC1|>", |
| "<|CCOc1ccc(C)cc1|>", |
| "<|NC(=O)CSc1nnco1|>", |
| "<|O=[SH](=O)Nc1ccccc1|>", |
| "<|O=[SH](=O)N1CCCCCC1|>", |
| "<|NC(=O)c1ccc(Cl)cc1|>", |
| "<|Cc1cc2ccccc2o1|>", |
| "<|Cc1ccc(N(C)C)cc1|>", |
| "<|c1ccc2cnccc2c1|>", |
| "<|Cc1cc2cncnc2s1|>", |
| "<|CC(=O)NC1CCCCC1|>", |
| "<|CC1CCN([SH](=O)=O)CC1|>", |
| "<|O=c1ccnc2sccn12|>", |
| "<|O=[SH](=O)c1ccc(Cl)cc1|>", |
| "<|Cc1ccccc1[N+](=O)[O-]|>", |
| "<|NC(=O)c1ccc(F)cc1|>", |
| "<|COc1ccc(C=O)cc1|>", |
| "<|Cc1ccc2ncsc2c1|>", |
| "<|Nc1ncnc2ncnc12|>", |
| "<|NC(=O)CSc1nnnn1|>", |
| "<|CCNC(=O)c1cccs1|>", |
| "<|CC(=O)N1CCCCCC1|>", |
| "<|Nc1ccc([N+](=O)[O-])cc1|>", |
| "<|O=C1Cc2ccccc2N1|>", |
| "<|CCOc1ccc(N)cc1|>", |
| "<|FC(F)(F)c1ccncn1|>", |
| "<|CC(=O)NCc1ccco1|>", |
| "<|Cc1c[nH]c2ccccc12|>", |
| "<|NC(=O)CN1CCNCC1|>", |
| "<|CCNC(=O)c1ccon1|>", |
| "<|Cc1ccc(OCF)cc1|>", |
| "<|CCOC(=O)c1ccsc1|>", |
| "<|O=CCCc1ccccc1|>", |
| "<|CS(=O)(=O)c1ccccc1|>", |
| "<|CCCOc1ccccc1|>", |
| "<|NC(=O)c1ccccc1O|>", |
| "<|NC(=O)c1ccccc1|>", |
| "<|FC(F)c1ccccc1|>", |
| "<|COc1cccc(C)c1|>", |
| "<|c1ccc2[nH]ccc2c1|>", |
| "<|COc1ccc(C)cc1|>", |
| "<|CCOc1ccccc1|>", |
| "<|O=C(O)c1ccccc1|>", |
| "<|O=[SH](=O)c1ccccc1|>", |
| "<|c1ccc2nccc2c1|>", |
| "<|O=CNc1ccccc1|>", |
| "<|c1ccc2ncnc2c1|>", |
| "<|O=[SH](=O)N1CCNCC1|>", |
| "<|c1ccc2scnc2c1|>", |
| "<|c1ccc2occc2c1|>", |
| "<|O=[N+]([O-])c1ccccc1|>", |
| "<|c1ccc2[nH]cnc2c1|>", |
| "<|O=[SH](=O)N1CCOCC1|>", |
| "<|cccc1ccccc1|>", |
| "<|NC(=O)C1CCNCC1|>", |
| "<|c1ccn2ccnc2c1|>", |
| "<|c1ccc2c(c1)OCO2|>", |
| "<|CC(=O)N1CCNCC1|>", |
| "<|c1ncc2ccsc2n1|>", |
| "<|COc1ccccc1C|>", |
| "<|CC(=O)N1CCOCC1|>", |
| "<|O=[SH](=O)N1CCCCC1|>", |
| "<|FCOc1ccccc1|>", |
| "<|Cccc1ccccc1|>", |
| "<|CC(=O)c1ccccc1|>", |
| "<|c1ccc2sccc2c1|>", |
| "<|c1ccc2ocnc2c1|>", |
| "<|Nc1cc(=O)[nH]c(=O)n1|>", |
| "<|c1cnc2ncnn2c1|>", |
| "<|COc1ccc(Cl)cc1|>", |
| "<|NC(=O)c1cccnc1|>", |
| "<|c1cnc2ccnn2c1|>", |
| "<|c1ncc2ncnc2n1|>", |
| "<|Cc1cc(C)cc(C)c1|>", |
| "<|c1cnn2cnnc2c1|>", |
| "<|Cn1c(=O)ccnc1=O|>", |
| "<|O=CCN1CCNCC1|>", |
| "<|c1ncc2cnnc2n1|>", |
| "<|N=Cc1ccccc1O|>", |
| "<|NCCc1ccccc1|>", |
| "<|COc1ccccc1O|>", |
| "<|COc1ccccc1Cl|>", |
| "<|CCCc1ccccc1|>", |
| "<|Cc1ccc(Cl)cc1Cl|>", |
| "<|CC(=O)N1CCCCC1|>", |
| "<|c1cc2c(s1)CCCC2|>", |
| "<|CCN1CCN(C)CC1|>", |
| "<|Cc1ccc(C)c(C)c1|>", |
| "<|CN(C)c1ccccc1|>", |
| "<|c1cnc2ncnc2c1|>", |
| "<|CNCc1ccccc1|>", |
| "<|O=COc1ccccc1|>", |
| "<|CCNc1ccccc1|>", |
| "<|c1ccc2c(c1)CCC2|>", |
| "<|CC(=O)NC1CCCC1|>", |
| "<|O=CNC1CCCCC1|>", |
| "<|NC(=O)c1ccncc1|>", |
| "<|O=Cc1ccccc1O|>", |
| "<|CC(=O)Nc1nccs1|>", |
| "<|CC(=O)Nc1nncs1|>", |
| "<|NC(=O)C1CCCNC1|>", |
| "<|c1cnc2sccc2c1|>", |
| "<|O=Cc1ccc(Cl)cc1|>", |
| "<|c1ncc2nnnc2n1|>", |
| "<|Cc1c(F)cccc1Cl|>", |
| "<|CC(=N)c1ccccc1|>", |
| "<|c1ncc2sccc2n1|>", |
| "<|c1ccc2nnnc2c1|>", |
| "<|Cc1ccc(Cl)c(Cl)c1|>", |
| "<|CC(C)c1ccccc1|>", |
| "<|COc1ccc(N)cc1|>", |
| "<|c1cnc2nccn2c1|>", |
| "<|O=C1CC(=O)NC(=O)N1|>", |
| "<|O=CNCc1ccco1|>", |
| "<|CCN1C(=O)CSC1=S|>", |
| "<|CCNC(=O)COC=O|>", |
| "<|c1ccn2cnnc2c1|>", |
| "<|N=Cc1ccc(O)cc1|>", |
| "<|COc1ccccc1F|>", |
| "<|CCCN1CCOCC1|>", |
| "<|CCOC(=O)N(C)CC|>", |
| "<|O=CC1=C(O)C(=O)NC1|>", |
| "<|CCC(=O)OCC(N)=O|>", |
| "<|COc1ccccc1|>", |
| "<|O=Cc1ccccc1|>", |
| "<|FCc1ccccc1|>", |
| "<|ccc1ccccc1|>", |
| "<|Cc1cccc(C)c1|>", |
| "<|Cc1ccccc1Cl|>", |
| "<|CCc1ccccc1|>", |
| "<|Cc1ccccc1C|>", |
| "<|N=Cc1ccccc1|>", |
| "<|Cc1ccc(C)cc1|>", |
| "<|CCN1CCOCC1|>", |
| "<|ccc1cncnc1|>", |
| "<|Cc1ccc(Cl)cc1|>", |
| "<|CCN1CCNCC1|>", |
| "<|Cc1ccc(F)cc1|>", |
| "<|O=CN1CCNCC1|>", |
| "<|NCc1ccccc1|>", |
| "<|OCc1ccccc1|>", |
| "<|CCCCCCCC|>", |
| "<|Cc1ccccc1F|>", |
| "<|Clc1cccc(Cl)c1|>", |
| "<|NC(=O)c1ccco1|>", |
| "<|O=c1ccnc(=O)[nH]1|>", |
| "<|Cc1ccc(O)cc1|>", |
| "<|Fc1cccc(F)c1|>", |
| "<|Cc1cccc(Cl)c1|>", |
| "<|CCCC(=O)NCC|>", |
| "<|N#Cc1ccccc1|>", |
| "<|N#Cc1cccnc1|>", |
| "<|CCCC(=O)OCC|>", |
| "<|Clc1ccccc1Cl|>", |
| "<|NC(=O)c1cccs1|>", |
| "<|CC(=O)OCC(N)=O|>", |
| "<|O=[SH](=O)N1CCCC1|>", |
| "<|CCN(CC)[SH](=O)=O|>", |
| "<|Cc1ccccc1O|>", |
| "<|CCN1CSCC1=O|>", |
| "<|O=c1ccnc(=O)n1|>", |
| "<|CC1CCCC(C)C1|>", |
| "<|SCc1ccccc1|>", |
| "<|nc1cncnc1n|>", |
| "<|Cc1cc(C)ncn1|>", |
| "<|CCN1CCCCC1|>", |
| "<|Cnc(=O)n(C)c=O|>", |
| "<|Cc1cccc(F)c1|>", |
| "<|CC(=O)NCC(N)=O|>", |
| "<|CNc1ccccc1|>", |
| "<|Cc1ccnc(C)c1|>", |
| "<|O=C1CCNC(=O)N1|>", |
| "<|NC(=O)CN[SH](=O)=O|>", |
| "<|CCC1=CCCCC1|>", |
| "<|Cc1cc(O)ncn1|>", |
| "<|O=cc1ccccc1|>", |
| "<|Cc1cccc(Br)c1|>", |
| "<|Cc1cccc(O)c1|>", |
| "<|O=CN1CCCCC1|>", |
| "<|NC(=O)c1ccon1|>", |
| "<|cc1ccccc1n|>", |
| "<|CC1NC(=O)NC1=O|>", |
| "<|Cc1ccccc1N|>", |
| "<|CN1CCN(C)CC1|>", |
| "<|Fc1ccccc1Cl|>", |
| "<|Clc1ccc(Cl)cc1|>", |
| "<|NC(=O)c1ccsc1|>", |
| "<|NC(=O)c1cnnn1|>", |
| "<|Fc1ccccc1F|>", |
| "<|Cc1ccc(Br)cc1|>", |
| "<|CCCCNC(C)=O|>", |
| "<|CSc1ccccc1|>", |
| "<|CNC[C@@H](O)C(C)C|>", |
| "<|O=Pc1ccccc1|>", |
| "<|Cc1ccc(N)cc1|>", |
| "<|c1nc2sccn2n1|>", |
| "<|Fc1cccc(Cl)c1|>", |
| "<|CCC(=O)N(C)CC|>", |
| "<|Cc1cc(=O)ncn1|>", |
| "<|Oc1ccccc1O|>", |
| "<|CCNC(=O)C(N)=O|>", |
| "<|CC1CNCC(C)C1|>", |
| "<|Oc1ccc(Cl)cc1|>", |
| "<|CCN(CC)C(C)=O|>", |
| "<|O=CC1CCCCC1|>", |
| "<|Oc1cccc(O)c1|>", |
| "<|NC(=O)C1CC=NO1|>", |
| "<|CCn1cnnc1S|>", |
| "<|CCNC(=O)NCC|>", |
| "<|NCc1cccnc1|>", |
| "<|Cc1ccccc1|>", |
| "<|Clc1ccccc1|>", |
| "<|Fc1ccccc1|>", |
| "<|Oc1ccccc1|>", |
| "<|Nc1ccccc1|>", |
| "<|CN1CCNCC1|>", |
| "<|CCNC(=O)CC|>", |
| "<|Cc1ccncn1|>", |
| "<|CC1CCCCC1|>", |
| "<|O=c1ccnc[nH]1|>", |
| "<|Cc1ccccn1|>", |
| "<|Brc1ccccc1|>", |
| "<|O=c1ccncn1|>", |
| "<|O=S1(=O)CCCC1|>", |
| "<|CCNC(=O)CS|>", |
| "<|Nc1ccncn1|>", |
| "<|Cc1cc(C)nn1|>", |
| "<|O=CCN[SH](=O)=O|>", |
| "<|CC(C)(C)OC=O|>", |
| "<|CCNC(=O)CO|>", |
| "<|CCOC(=O)CC|>", |
| "<|NC(=O)CNC=O|>", |
| "<|CCCNC(C)=O|>", |
| "<|Oc1ccncn1|>", |
| "<|Clc1cccnc1|>", |
| "<|Cc1ccc(C)n1|>", |
| "<|nc1ccccc1|>", |
| "<|Cc1cccnc1|>", |
| "<|nc1ncccn1|>", |
| "<|CNCCC(C)C|>", |
| "<|CN1CCOCC1|>", |
| "<|Cc1cc(C)on1|>", |
| "<|NC(=O)COC=O|>", |
| "<|CC(=O)NCC=O|>", |
| "<|Sc1ccccc1|>", |
| "<|CCNCC(N)=O|>", |
| "<|CCCC(=O)OC|>", |
| "<|CC1CCCNC1|>", |
| "<|Cnc(=O)nc=O|>", |
| "<|CN1CCCCC1|>", |
| "<|Nc1ncncn1|>", |
| "<|cc1ncnc1n|>", |
| "<|CC(=O)NC(C)C|>", |
| "<|CC1CCNCC1|>", |
| "<|O=c1ccccn1|>", |
| "<|Cc1ccsc1C|>", |
| "<|oc1ccccc1|>", |
| "<|O=cc1cncn1|>", |
| "<|CCNC(=O)CN|>", |
| "<|CCN(C)[SH](=O)=O|>", |
| "<|Cc1cccnn1|>", |
| "<|O=c1cccnn1|>", |
| "<|NC1CCCCC1|>", |
| "<|Cn1cnnc1S|>", |
| "<|Clc1ccccn1|>", |
| "<|CCCCC(N)=O|>", |
| "<|Oc1ccccn1|>", |
| "<|NCc1ccco1|>", |
| "<|OCCOCCO|>", |
| "<|CC(C)CC(N)=O|>", |
| "<|CCCCCCC|>", |
| "<|CCCCNC=O|>", |
| "<|Cc1ccncc1|>", |
| "<|CCCN[SH](=O)=O|>", |
| "<|O=Cc1cccs1|>", |
| "<|Cc1c[nH]c(C)c1|>", |
| "<|O=Cc1ccco1|>", |
| "<|O=C1CNC(=O)N1|>", |
| "<|O=C1CCC(=O)N1|>", |
| "<|O=C1CNCCN1|>", |
| "<|O=C1CSC(=S)N1|>", |
| "<|Nc1ncccn1|>", |
| "<|NC1=NC(=O)CS1|>", |
| "<|CCN(C=O)CC|>", |
| "<|Cc1ccc(C)o1|>", |
| "<|N#Cc1cocn1|>", |
| "<|CSc1ncnn1|>", |
| "<|CCN1CCCC1|>", |
| "<|C1CCCNCC1|>", |
| "<|CCC1OCCO1|>", |
| "<|CC(=O)OCC=O|>", |
| "<|C1CCCCCC1|>", |
| "<|CC(=O)CC(C)C|>", |
| "<|CCCCNCC|>", |
| "<|CC(=O)OCCO|>", |
| "<|CCNS(C)(=O)=O|>", |
| "<|Nn1cnnc1S|>", |
| "<|CC(=O)NCCO|>", |
| "<|Cc1cccn1C|>", |
| "<|CCOC(=O)CN|>", |
| "<|CCCCC(=O)O|>", |
| "<|Brc1cccnc1|>", |
| "<|nc1ccncn1|>", |
| "<|O=c1ncccn1|>", |
| "<|CCN(CC)CC|>", |
| "<|OCc1cnnn1|>", |
| "<|CCCCCCO|>", |
| "<|CCc1nncs1|>", |
| "<|sc1ccccc1|>", |
| "<|O=C1CSC(=O)N1|>", |
| "<|O=C1NCC=C1O|>", |
| "<|Cc1ccn(C)n1|>", |
| "<|c1ccccc1|>", |
| "<|c1ccncc1|>", |
| "<|c1cncnc1|>", |
| "<|CCN[SH](=O)=O|>", |
| "<|CCNC(C)=O|>", |
| "<|C1CNCCN1|>", |
| "<|Cc1ccco1|>", |
| "<|Cc1ccnn1|>", |
| "<|Cc1cccs1|>", |
| "<|C1COCCN1|>", |
| "<|CCOC(C)=O|>", |
| "<|CCCC(N)=O|>", |
| "<|C1CCNCC1|>", |
| "<|Sc1ncnn1|>", |
| "<|Cc1ccno1|>", |
| "<|O=CCNC=O|>", |
| "<|C1CCCCC1|>", |
| "<|Cc1cccn1|>", |
| "<|CCCC(C)C|>", |
| "<|c1ccnnc1|>", |
| "<|CCNC(N)=O|>", |
| "<|cccncn|>", |
| "<|c1cnccn1|>", |
| "<|cccccn|>", |
| "<|CCCNCC|>", |
| "<|Cc1cscn1|>", |
| "<|CCNCC=O|>", |
| "<|Cc1ccc[nH]1|>", |
| "<|CCCNC=O|>", |
| "<|CC1CCCO1|>", |
| "<|c1ncncn1|>", |
| "<|CNCC(N)=O|>", |
| "<|c1cnncn1|>", |
| "<|CCCCCC|>", |
| "<|c1cc[n+]cc1|>", |
| "<|nc(=O)nc=O|>", |
| "<|Cn1cccn1|>", |
| "<|c1ccocc1|>", |
| "<|CCC(=O)NC|>", |
| "<|O=C1CSCN1|>", |
| "<|CCOCCO|>", |
| "<|CCC(=O)OC|>", |
| "<|CC(C)NC=O|>", |
| "<|O=C1CCCN1|>", |
| "<|Cc1ccsc1|>", |
| "<|Cn1ccnc1|>", |
| "<|Nc1nccs1|>", |
| "<|Cc1cnco1|>", |
| "<|CCN(C)CC|>", |
| "<|CN(C)[SH](=O)=O|>", |
| "<|cccc(n)=O|>", |
| "<|CCCC(=O)O|>", |
| "<|COC(=O)CN|>", |
| "<|cc1cccs1|>", |
| "<|CC(C)C(N)=O|>", |
| "<|CCN(C)C=O|>", |
| "<|CCN=C(N)S|>", |
| "<|N#CCC(N)=O|>", |
| "<|Cn1cccc1|>", |
| "<|O=CCCC=O|>", |
| "<|Cc1cc[nH]n1|>", |
| "<|NC(=O)C(N)=O|>", |
| "<|CCNC(=N)S|>", |
| "<|Nc1cnon1|>", |
| "<|Cc1nncs1|>", |
| "<|O=CCOC=O|>", |
| "<|CCCCCO|>", |
| "<|ccccco|>", |
| "<|Cc1ccon1|>", |
| "<|cccc(C)n|>", |
| "<|Nc1nncs1|>", |
| "<|CCNC(N)=S|>", |
| "<|Brc1cccs1|>", |
| "<|Nc1ncnn1|>", |
| "<|Clc1cccs1|>", |
| "<|C1=CCCCC1|>", |
| "<|COC(C)(C)C|>", |
| "<|CC(C)CCO|>", |
| "<|NC(=O)C1CC1|>", |
| "<|cccc(c)C|>", |
| "<|CCCN(C)C|>", |
| "<|CCC(C)CC|>", |
| "<|CN1CCCC1|>", |
| "<|CNC(=O)CS|>", |
| "<|NCCCCF|>", |
| "<|CC(C)CCN|>", |
| "<|Cc1nccs1|>", |
| "<|CCNCCO|>", |
| "<|CC(C)OC=O|>", |
| "<|OCC(O)CO|>", |
| "<|Sc1nnco1|>", |
| "<|ccccC=O|>", |
| "<|CCNCC|>", |
| "<|ccccC|>", |
| "<|CCNC=O|>", |
| "<|ccccn|>", |
| "<|c1cnnc1|>", |
| "<|c1ccsc1|>", |
| "<|c1ncnn1|>", |
| "<|c1cscn1|>", |
| "<|NC(=O)CS|>", |
| "<|c1cnoc1|>", |
| "<|c1ccoc1|>", |
| "<|CCCC=O|>", |
| "<|CCC(N)=O|>", |
| "<|CCCCC|>", |
| "<|c1nncs1|>", |
| "<|c1nnnn1|>", |
| "<|NC(=O)CO|>", |
| "<|CCOC=O|>", |
| "<|ccccc|>", |
| "<|c1cncn1|>", |
| "<|c1nnco1|>", |
| "<|c1cn[nH]c1|>", |
| "<|ncnc=O|>", |
| "<|c1cnnn1|>", |
| "<|C1CCCC1|>", |
| "<|c1cocn1|>", |
| "<|CNC(C)=O|>", |
| "<|CCN(C)C|>", |
| "<|c1ncon1|>", |
| "<|c1ccnc1|>", |
| "<|CCCCO|>", |
| "<|COC(C)=O|>", |
| "<|CN[SH](=O)=O|>", |
| "<|NCC(N)=O|>", |
| "<|CCCCN|>", |
| "<|CCNCS|>", |
| "<|c1c[nH]cn1|>", |
| "<|CCC(C)C|>", |
| "<|CNCC=O|>", |
| "<|CCC(=O)O|>", |
| "<|CCC(C)=O|>", |
| "<|CCCNC|>", |
| "<|C1CCNC1|>", |
| "<|c1cnon1|>", |
| "<|cccc=O|>", |
| "<|nccc=O|>", |
| "<|CC(N)C=O|>", |
| "<|ncncn|>", |
| "<|c1cc[nH]c1|>", |
| "<|c1nc[nH]n1|>", |
| "<|c1csnn1|>", |
| "<|CC(=O)NN|>", |
| "<|CS(N)(=O)=O|>", |
| "<|CC(O)CO|>", |
| "<|c1cnsc1|>", |
| "<|NC(=O)C=O|>", |
| "<|ccncn|>", |
| "<|COCCO|>", |
| "<|ncc(n)=O|>", |
| "<|CC(C)(C)N|>", |
| "<|NCC(=O)O|>", |
| "<|CCOP=O|>", |
| "<|CCCOC|>", |
| "<|CC(O)CF|>", |
| "<|ncncs|>", |
| "<|ccc(=O)o|>", |
| "<|COCCN|>", |
| "<|cccc[nH]|>", |
| "<|O=C(O)CS|>", |
| "<|CC[SH](=O)=O|>", |
| "<|O=C(O)CO|>", |
| "<|O=ccco|>", |
| "<|OCC(F)F|>", |
| "<|CC(C)CN|>", |
| "<|CCOCC|>", |
| "<|OCCCO|>", |
| "<|CCNC=S|>", |
| "<|ccc(C)n|>", |
| "<|[nH]cnc=O|>", |
| "<|Cnc([nH])=O|>", |
| "<|CC(C)C=O|>", |
| "<|c1ncsn1|>", |
| "<|NC(=O)CCl|>", |
| "<|NCC(F)F|>", |
| "<|CN(C)C=O|>", |
| "<|CC(C)(C)O|>", |
| "<|CNCCO|>", |
| "<|c1nn[nH]n1|>", |
| "<|cccc|>", |
| "<|CC(N)=O|>", |
| "<|CCCC|>", |
| "<|CCNC|>", |
| "<|cncn|>", |
| "<|CCC=O|>", |
| "<|cccn|>", |
| "<|N[SH](=O)=O|>", |
| "<|CC(C)C|>", |
| "<|CC(=O)O|>", |
| "<|ncnn|>", |
| "<|NCC=O|>", |
| "<|CCCO|>", |
| "<|nccn|>", |
| "<|OCCO|>", |
| "<|O=CCO|>", |
| "<|ccc=O|>", |
| "<|CC(C)O|>", |
| "<|CCCN|>", |
| "<|COC=O|>", |
| "<|FC(F)F|>", |
| "<|CC(C)N|>", |
| "<|CNC=O|>", |
| "<|NC(N)=O|>", |
| "<|C[SH](=O)=O|>", |
| "<|O=CCS|>", |
| "<|CCOC|>", |
| "<|CCC#N|>", |
| "<|NNC=O|>", |
| "<|NCCO|>", |
| "<|N=C(N)S|>", |
| "<|Cncn|>", |
| "<|CC(C)=O|>", |
| "<|CN(C)C|>", |
| "<|NC(N)=S|>", |
| "<|OCCF|>", |
| "<|[nH]c(n)=O|>", |
| "<|cc(C)n|>", |
| "<|CCCS|>", |
| "<|O=[PH](O)O|>", |
| "<|cc(n)=O|>", |
| "<|CCSC|>", |
| "<|NCCF|>", |
| "<|nc(=O)o|>", |
| "<|Ccnn|>", |
| "<|O=[SH](=O)O|>", |
| "<|N=C(N)N|>", |
| "<|C[Si]C|>", |
| "<|ncc=O|>", |
| "<|C=CCO|>", |
| "<|ccnn|>", |
| "<|CCN|>", |
| "<|CCC|>", |
| "<|CCO|>", |
| "<|ccn|>", |
| "<|O=S=O|>", |
| "<|NC=O|>", |
| "<|ncn|>", |
| "<|CC=O|>", |
| "<|O=CO|>", |
| "<|ncs|>", |
| "<|O=[N+][O-]|>", |
| "<|ccc|>", |
| "<|CNC|>", |
| "<|nco|>", |
| "<|FCF|>", |
| "<|nc[nH]|>", |
| "<|NC=S|>", |
| "<|CC=N|>", |
| "<|[nH]cn|>", |
| "<|NCS|>", |
| "<|C=CC|>", |
| "<|CCS|>", |
| "<|ccs|>", |
| "<|O=PO|>", |
| "<|nc=O|>", |
| "<|N=CN|>", |
| "<|CC#N|>", |
| "<|cc=O|>", |
| "<|C1CC1|>", |
| "<|Ccn|>", |
| "<|C[N+]C|>", |
| "<|O=[S+][O-]|>", |
| "<|cc[n+]|>", |
| "<|C[Si]|>", |
| "<|[nH]c=O|>", |
| "<|OCO|>", |
| "<|NCO|>", |
| "<|nsn|>", |
| "<|cnn|>", |
| "<|CCCl|>", |
| "<|COC|>", |
| "<|cco|>", |
| "<|nnn|>", |
| "<|cc[nH]|>", |
| "<|O=co|>", |
| "<|non|>", |
| "<|cc|>", |
| "<|CC|>", |
| "<|cn|>", |
| "<|CO|>", |
| "<|O=S|>", |
| "<|CN|>", |
| "<|[N+][O-]|>", |
| "<|CF|>", |
| "<|CS|>", |
| "<|C=O|>", |
| "<|c=O|>", |
| "<|C#N|>", |
| "<|nn|>", |
| "<|C=N|>", |
| "<|O=P|>", |
| "<|NN|>", |
| "<|ns|>", |
| "<|[O-][S+]|>", |
| "<|C[N+]|>", |
| "<|NO|>", |
| "<|c[nH]|>", |
| "<|no|>", |
| "<|N=N|>", |
| "<|cs|>", |
| "<|[n+][O-]|>", |
| "<|CCl|>", |
| "<|[B]|>", |
| "<|[Br]|>", |
| "<|[C]|>", |
| "<|[Cl]|>", |
| "<|[F]|>", |
| "<|[I]|>", |
| "<|[N]|>", |
| "<|[O]|>", |
| "<|[P]|>", |
| "<|[S]|>" |
| ], |
| "bos_token": { |
| "content": "<|begin_of_text|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false |
| }, |
| "eos_token": { |
| "content": "<|eot_id|>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false |
| }, |
| "pad_token": { |
| "content": "<pad>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false |
| } |
| } |
|
|