List your company

Safety Evaluation on LLaMA-2-7B-CHAT (test)

0.55Safety ScoreTRAP
0.41480.44990.4850.5201Oct 11, 2024

Evaluation results

MethodLinks
TRAPalpha=0.90, merging_technique=TIES-merging, DARE=true2024.100.55
TRAPalpha=0.70, merging_technique=TIES-merging, DARE=true2024.100.54
MERGEPRINTalpha=0.90, merging_technique=TIES-merging, DARE=true2024.100.54
MERGEPRINTalpha=0.70, merging_technique=TIES-merging, DARE=true2024.100.53
TRAPalpha=0.50, merging_technique=TIES-merging, DARE=true2024.100.52
TRAPalpha=0.90, merging_technique=TIES-merging, DARE=false2024.100.51
MERGEPRINTalpha=0.90, merging_technique=TIES-merging, DARE=false2024.100.51
MERGEPRINTalpha=0.50, merging_technique=TIES-merging, DARE=true2024.100.51
TRAPalpha=0.90, merging_technique=Task Arithmetic, DARE=false2024.100.5
TRAPalpha=0.90, merging_technique=Task Arithmetic, DARE=true2024.100.5
TRAPalpha=0.70, merging_technique=TIES-merging, DARE=false2024.100.5
IFalpha=0.50, merging_technique=TIES-merging, DARE=true2024.100.5
MERGEPRINTalpha=0.90, merging_technique=Task Arithmetic, DARE=false2024.100.5
MERGEPRINTalpha=0.90, merging_technique=Task Arithmetic, DARE=true2024.100.5
TRAPalpha=0.50, merging_technique=TIES-merging, DARE=false2024.100.49
IFalpha=0.70, merging_technique=TIES-merging, DARE=true2024.100.49
MERGEPRINTalpha=0.70, merging_technique=TIES-merging, DARE=false2024.100.49
TRAPalpha=0.30, merging_technique=TIES-merging, DARE=true2024.100.48
IFalpha=0.10, merging_technique=TIES-merging, DARE=true2024.100.48
IFalpha=0.30, merging_technique=TIES-merging, DARE=true2024.100.48
IFalpha=0.90, merging_technique=TIES-merging, DARE=true2024.100.48
MERGEPRINTalpha=0.50, merging_technique=TIES-merging, DARE=false2024.100.48
IFalpha=0.90, merging_technique=Task Arithmetic, DARE=false2024.100.47
IFalpha=0.90, merging_technique=Task Arithmetic, DARE=true2024.100.47
IFalpha=0.90, merging_technique=TIES-merging, DARE=false2024.100.47
MERGEPRINTalpha=0.30, merging_technique=TIES-merging, DARE=true2024.100.47
TRAPalpha=0.70, merging_technique=Task Arithmetic, DARE=false2024.100.46
TRAPalpha=0.70, merging_technique=Task Arithmetic, DARE=true2024.100.46
TRAPalpha=0.10, merging_technique=TIES-merging, DARE=true2024.100.46
IFalpha=0.70, merging_technique=Task Arithmetic, DARE=false2024.100.46
IFalpha=0.70, merging_technique=Task Arithmetic, DARE=true2024.100.46
IFalpha=0.50, merging_technique=TIES-merging, DARE=false2024.100.46
IFalpha=0.70, merging_technique=TIES-merging, DARE=false2024.100.46
MERGEPRINTalpha=0.10, merging_technique=TIES-merging, DARE=true2024.100.46
TRAPalpha=0.30, merging_technique=TIES-merging, DARE=false2024.100.45
IFalpha=0.30, merging_technique=TIES-merging, DARE=false2024.100.45
MERGEPRINTalpha=0.70, merging_technique=Task Arithmetic, DARE=false2024.100.45
MERGEPRINTalpha=0.70, merging_technique=Task Arithmetic, DARE=true2024.100.45
MERGEPRINTalpha=0.30, merging_technique=TIES-merging, DARE=false2024.100.45
TRAPalpha=0.50, merging_technique=Task Arithmetic, DARE=false2024.100.44
TRAPalpha=0.50, merging_technique=Task Arithmetic, DARE=true2024.100.44
IFalpha=0.50, merging_technique=Task Arithmetic, DARE=false2024.100.44
IFalpha=0.50, merging_technique=Task Arithmetic, DARE=true2024.100.44
IFalpha=0.10, merging_technique=TIES-merging, DARE=false2024.100.44
MERGEPRINTalpha=0.50, merging_technique=Task Arithmetic, DARE=false2024.100.44
MERGEPRINTalpha=0.50, merging_technique=Task Arithmetic, DARE=true2024.100.44
MERGEPRINTalpha=0.10, merging_technique=TIES-merging, DARE=false2024.100.44
TRAPalpha=0.30, merging_technique=Task Arithmetic, DARE=false2024.100.43
TRAPalpha=0.30, merging_technique=Task Arithmetic, DARE=true2024.100.43
TRAPalpha=0.10, merging_technique=TIES-merging, DARE=false2024.100.43
IFalpha=0.10, merging_technique=Task Arithmetic, DARE=false2024.100.43
IFalpha=0.30, merging_technique=Task Arithmetic, DARE=false2024.100.43
IFalpha=0.10, merging_technique=Task Arithmetic, DARE=true2024.100.43
IFalpha=0.30, merging_technique=Task Arithmetic, DARE=true2024.100.43
MERGEPRINTalpha=0.30, merging_technique=Task Arithmetic, DARE=false2024.100.43
MERGEPRINTalpha=0.30, merging_technique=Task Arithmetic, DARE=true2024.100.43
TRAPalpha=0.10, merging_technique=Task Arithmetic, DARE=false2024.100.42
TRAPalpha=0.10, merging_technique=Task Arithmetic, DARE=true2024.100.42
MERGEPRINTalpha=0.10, merging_technique=Task Arithmetic, DARE=false2024.100.42
MERGEPRINTalpha=0.10, merging_technique=Task Arithmetic, DARE=true2024.100.42