ictnlp/LLaVA-Mini

LLaVA-Mini is a unified large multimodal model (LMM) that can support the understanding of images, high-resolution images, and videos in an efficient manner.

⭐ 577 ⑂ 34 Python Apache-2.0 · 2025-06-29推送

gpt4o large-language-models llama llava multimodal video vision vision-language-model large-multimodal-models gpt4v multimodal-large-language-models efficient visual-instruction-tuning

577

Watchers

0

贡献者

0

Commits

0

Releases

30

Open Issues

2025-06-29

最近推送

原文中文

暂无 README