https://github.com/deepseek-ai/DeepSeek-VL

DeepSeek-VL: Towards Real-World Vision-Language Understanding
https://github.com/deepseek-ai/DeepSeek-VL

foundation-models vision-language-model vision-language-pretraining

Last synced: 16 days ago
JSON representation

DeepSeek-VL: Towards Real-World Vision-Language Understanding

• Host: GitHub
• URL: https://github.com/deepseek-ai/DeepSeek-VL
• Owner: deepseek-ai
• License: mit
• Created: 2024-03-07T08:32:57.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-04-24T05:01:06.000Z (12 months ago)
• Last Synced: 2025-03-30T10:02:33.045Z (22 days ago)
• Topics: foundation-models, vision-language-model, vision-language-pretraining
• Language: Python
• Homepage: https://huggingface.co/spaces/deepseek-ai/DeepSeek-VL-7B
• Size: 12.2 MB
• Stars: 3,738
• Watchers: 35
• Forks: 555
• Open Issues: 38
• Metadata Files:
  • Readme: README.md
  • License: LICENSE-CODE

Awesome Lists containing this project

• awesome-deepseek - 🖼️ DeepSeek-VL - Vision-language model for real-world understanding (1.3B/7B), 4096 context length (Models / Multimodal Models)
• awesome-deepseek - 🖼️ DeepSeek-VL - Vision-language model for real-world understanding (1.3B/7B), 4096 context length (Models / Multimodal Models)
• StarryDivineSky - deepseek-ai/DeepSeek-VL - VL具备通用的多模态理解能力，能够在复杂场景下处理逻辑图、网页、公式识别、科学文献、自然图像和具身智能。 (其他_机器视觉 / 网络服务_其他)
• Awesome-Segment-Anything - [code
• AiTreasureBox - deepseek-ai/DeepSeek-VL - 04-15_3775_0](https://img.shields.io/github/stars/deepseek-ai/DeepSeek-VL.svg)|DeepSeek-VL: Towards Real-World Vision-Language Understanding| (Repos)