https://github.com/NiuTrans/Vision-LLM-Alignment
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.
https://github.com/NiuTrans/Vision-LLM-Alignment
alignment dpo llama3-vision llava llm mllm multi-model ppo reward rlhf sft vision
Last synced: about 1 month ago
JSON representation
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.
- Host: GitHub
- URL: https://github.com/NiuTrans/Vision-LLM-Alignment
- Owner: NiuTrans
- Created: 2024-06-29T14:53:25.000Z (12 months ago)
- Default Branch: master
- Last Pushed: 2024-10-16T10:25:30.000Z (8 months ago)
- Last Synced: 2025-04-06T07:14:53.735Z (2 months ago)
- Topics: alignment, dpo, llama3-vision, llava, llm, mllm, multi-model, ppo, reward, rlhf, sft, vision
- Language: Python
- Homepage:
- Size: 153 MB
- Stars: 104
- Watchers: 3
- Forks: 8
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-LLM-resources - Vision-LLM Alignemnt - based LLMs, including the LLaVA models and the LLaMA-3.2-vision models. (微调 Fine-Tuning)