Vision-LLM-Alignment

Vision alignment framework

A framework for training vision-based large language models to improve their alignment and performance

This repository contains the code for SFT, RLHF, and DPO, designed for vision-based LLMs, including the LLaVA models and the LLaMA-3.2-vision models.

GitHub

2 stars
0 watching
0 forks
Language: Python
last commit: 3 months ago