The de facto standard implementation of the YOLO series: detection, segmentation, pose estimation and tracking in one place.
LLaVA
视觉指令微调的多模态大模型，开启 GPT-4V 级开源探索。
- Category
- 👁️ Computer Vision
- Repository
- haotian-liu/LLaVA
- Stars
- ★ 25,072
- Forks
- 2,774
- Language
- Python
- License
- Apache-2.0
- Last updated
- 2024-08-12
- Visits
- 0
Multimodal
