zephyr_0.1_a8.0 / README.md
chujiezheng's picture
Create README.md
d23c2df verified
---
license: apache-2.0
language:
- en
---
# zephyr_0.1_a8.0
The extrapolated (ExPO) model based on `chujiezheng/zephyr_0.1` and `alignment-handbook/zephyr-7b-sft-full`, as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper.
Specifically, we obtain this model by extrapolating from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.