README.md

metadata

pipeline_tag: text-generation
license: other
language:
  - en
  - zh

internlm2-chat-1_8b-ExPO

The extrapolated (ExPO) model based on internlm2-chat-1_8b and internlm/internlm2-chat-1_8b-sft, 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.