chujiezheng's picture
Create README.md
565016f verified
|
raw
history blame
411 Bytes
metadata
license: apache-2.0
language:
  - en

The extrapolated (ExPO) model based on berkeley-nest/Starling-LM-7B-alpha and openchat/openchat_3.5, as in the "Weak-to-Strong Extrapolation Expedites Alignment" paper.

Specifically, we obtain this model by extrapolating from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.