Model Checkpoints in the ExPO Paper
Collection
15 items
•
Updated
•
2
zephyr_0.2_a2.5
The extrapolated (ExPO) model based on chujiezheng/zephyr_0.2 and alignment-handbook/zephyr-7b-sft-full, 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.
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.