metadata
license: apache-2.0
language:
- en
Starling-LM-7B-beta-ExPO
The extrapolated (ExPO) model based on Nexusflow/Starling-LM-7B-beta and openchat/openchat-3.5-0106, as in the "Weak-to-Strong Extrapolation Expedites Alignment" paper.
Specifically, we obtain this model by extrapolating (alpha = 0.5) from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.