List your company

Dialogue on Dialogue

77.79PandaLMHBAT
44.021252.788161.55570.3219Jun 21, 2024

Evaluation results

MethodLinks
HBAT#Param=13B, PPO=false, DPO=true2024.0677.79-4.7867.45
HBAT-Freeze#Param=13B, PPO=false, DPO=true2024.0676.87-5.0165.62
DPO#Param=13B, PPO=false, DPO=true2024.0675-5.0764.31
HBAT#Param=7B, PPO=false, DPO=true2024.0674.78-5.2258.1
HBAT#Param=13B, PPO=true, DPO=false2024.0672.83-5.1162.32
RLHF#Param=13B, PPO=true, DPO=false2024.0672.21-5.6561.16
HBAT-Freeze#Param=13B, PPO=true, DPO=false2024.0671.31-5.4956.37
HBAT#Param=7B, PPO=true, DPO=false2024.0670.88-5.3757.12
DPO#Param=7B, PPO=false, DPO=true2024.0670.74-5.7254.23
HBAT-Freeze#Param=7B, PPO=true, DPO=false2024.0669.91-5.9156.19
RLHF#Param=7B, PPO=true, DPO=false2024.0669.79-5.8155.63
HBAT-Freeze#Param=7B, PPO=false, DPO=true2024.0668.78-5.4156.95
RLHF+pt#Param=13B, PPO=true, DPO=false2024.0663.67-6.9754.45
SFT#Param=13B, PPO=false, DPO=false2024.0662.16-6.3246.11
SFT#Param=7B, PPO=false, DPO=false2024.0654.76-6.7943.49
SFT+ppo#Param=13B, PPO=true, DPO=false2024.0654-7.9343.12
RLHF+pt#Param=7B, PPO=true, DPO=false2024.0653.52-7.0954.18
SFT+ppo#Param=7B, PPO=true, DPO=false2024.0645.32-8.642.25