DPO LoRA Adapter for Instruction Alignment

This repository provides a LoRA adapter fine-tuned with Direct Preference Optimization (DPO) for improving instruction-following behavior and safety alignment.

Notes

  • This repository contains only LoRA adapter weights.
  • The tokenizer should be loaded from the base model.
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support