---
library_name: transformers
datasets:
- wzhouad/llama3-ultrafeedback-hybrid
---

## Description

Llama3-Instruct-8B model finetuned by hybrid WPO (GPT-4-turbo + on-policy sampling + Ultrafeedback). Details in [WPO: Enhancing RLHF with Weighted Preference Optimization](https://arxiv.org/abs/2406.11827). The model is trained based on [wzhouad/llama3-ultrafeedback-hybrid](https://huggingface.co/datasets/wzhouad/llama3-ultrafeedback-hybrid).

## License
This model is licensed under the Zoom software license and is permitted for use only for noncommercial, educational, or academic research purposes.