MiniGPT-4

MiniGPT-VMiniGPT-v2: Large Language Model as a Unified Interface for Vision-Language Multi-task LearningJun Chen, Deyao Zhu, Xiaoqian Shen, Xiang Li, Zechun Liu, Pengchuan Zhang, Raghuraman Krishnamoorthi, Vikas Chandra, Yunyang Xiong☨, Mohamed Elhoseiny☨☨equal last author    MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language ModelsDeyao Zhu*, Jun Chen*, Xiaoqian Shen, Xiang Li, Mohamed Elhoseiny*equal contribution     King Abdullah University of Science and Technology AcknowledgementBLIP2 The model architecture of MiniGPT-4 follows BLIP-2. Don't forget to check this great open-source work if you don't know it before!Lavis This repository is built upon Lavis!Vicuna The fantastic language ability of Vicuna with only 13B parameters is just amazing. And it is open-source!LLaMA The strong open-sourced LLaMA 2 language model.If you're using MiniGPT-4/MiniGPT-v2 in your research or applications, please cite using this BibTeX:@article{chen2023minigptv2, title={MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning}, author={Chen, Jun and Zhu, Deyao and Shen, Xiaoqian and Li, Xiang and Liu, Zechu and Zhang, Pengchuan and Krishnamoorthi, Raghuraman and Chandra, Vikas and Xiong, Yunyang and Elhoseiny, Mohamed}, year={2023}, journal={arXiv preprint arXiv:2310.09478},}@article{zhu2023minigpt, title={MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models}, author={Zhu, Deyao and Chen, Jun and Shen, Xiaoqian and Li, Xiang and Elhoseiny, Mohamed}, journal={arXiv preprint arXiv:2304.10592}, year={2023}} LicenseThis repository is under BSD 3-Clause License. Many codes are based on Lavis with BSD 3-Clause License here.