metadata
pipeline_tag: text-generation
license: other
language:
- en
- zh
internlm2-chat-20b-ExPO
The extrapolated (ExPO) model based on internlm2-chat-20b and internlm/internlm2-chat-20b-sft, 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.