1.haotian-liu / LLaVA[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.gpt-4chatbotchatgptllamamultimodalllava+7 morePythonAPACHE-2.025K total2.8K forks+2 starsfrom 25,078 · score 1.10
2.OpenGVLab / InternVL[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型image-classificationimage-text-retrievalllmsemantic-segmentationvideo-classificationvision-language-model+6 morePythonMIT10K total791 forks+2 starsfrom 10,171 · score 1.10