A Survey of Direct Preference Optimization

Official Implementation (Pytorch) of the "VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning", AAAI 2025

Notebooks to create an instruction following version of Microsoft's Phi 2 LLM with Supervised Fine Tuning and Direct Preference Optimization (DPO)

Notebooks to create an instruction following version of Microsoft's Phi 1.5 LLM with Supervised Fine Tuning and Direct Preference Optimization (DPO)

The Rap Music Generator project is an innovative LLM-based tool designed to create rap lyrics. It offers multiple fine-tuning approaches to accommodate diverse rap generation techniques, providing users with a versatile platform for generating unique and stylistically varied content.

EPFLLaMA: A lightweight language model fine-tuned on EPFL curriculum content. Specialized for STEM education and multiple-choice question answering. Implements advanced techniques like SFT, DPO, and quantization.

[Paper: CC (Springer) 2025] [Official code] - Engaging preference optimization alignment in large language model for continual radiology report generation: A hybrid approach

EPFLLaMA: A lightweight language model fine-tuned on EPFL curriculum content. Specialized for STEM education and multiple-choice question answering. Implements advanced techniques like SFT, DPO, and quantization.

Enhancing paraphrase-type generation using Direct Preference Optimization (DPO) and Reinforcement Learning from Human Feedback (RLHF), with large-scale HPC support. This project aligns model outputs to human-ranked data for robust, safety-focused NLP.