The de facto standard implementation of the YOLO series: detection, segmentation, pose estimation and tracking in one place.
Qwen2.5-VL
通义千问视觉语言模型，擅长文档、图表与视频理解。
- Category
- 👁️ Computer Vision
- Repository
- QwenLM/Qwen2.5-VL
- Stars
- ★ 20,082
- Forks
- 1,869
- Language
- Jupyter Notebook
- License
- Apache-2.0
- Last updated
- 2026-01-30
- Visits
- 0
Vision-language
