File size: 563 Bytes
483c322 27ce9e6 |
1 2 3 4 5 6 7 8 9 10 11 |
---
language:
- en
license: llama3
---
# LLaMA3-iterative-DPO-final-ExPO
The extrapolated (ExPO) model based on [`RLHFlow/LLaMA3-iterative-DPO-final`](https://huggingface.co/RLHFlow/LLaMA3-iterative-DPO-final) and [`RLHFlow/LLaMA3-SFT`](https://huggingface.co/RLHFlow/LLaMA3-SFT), as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper.
Specifically, we obtain this model by extrapolating **(alpha = 0.3)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference. |