deepseek-ai/DeepSeek-VL
DeepSeek-VL is a vision-language foundation model for real-world multimodal comprehension.
Not currently ranked — collecting fresh signals.
star history
DeepSeek-VL is a vision-language model that combines visual and language understanding capabilities. The repository provides model weights, training code, and inference tools for the VL model. It enables tasks like visual question answering and image-text comprehension across real-world scenarios.
Frequently asked
- What is deepseek-ai/DeepSeek-VL?
- DeepSeek-VL is a vision-language foundation model for real-world multimodal comprehension.
- Is DeepSeek-VL open source?
- Yes — deepseek-ai/DeepSeek-VL is open source, released under the MIT license.
- What language is DeepSeek-VL written in?
- deepseek-ai/DeepSeek-VL is primarily written in Python.
- How popular is DeepSeek-VL?
- deepseek-ai/DeepSeek-VL has 4.1k stars on GitHub.
- Where can I find DeepSeek-VL?
- deepseek-ai/DeepSeek-VL is on GitHub at https://github.com/deepseek-ai/DeepSeek-VL.