Weak-to-Strong Extrapolation Expedites Alignment
Collection
Better aligned models obtained by weak-to-strong model extrapolation (ExPO)
•
23 items
•
Updated
•
1
The extrapolated (ExPO) model based on alignment-handbook/zephyr-7b-dpo-full
and alignment-handbook/zephyr-7b-sft-full
, as in the "Weak-to-Strong Extrapolation Expedites Alignment" paper.
Specifically, we obtain this model by extrapolating (alpha = 0.3) from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.