Deepseek-VL2

Deepseek-VL2

MoE Vision-Language, Now Easier to Access

585 followers

DeepSeek-VL2 are open-source vision-language models with strong multimodal understanding, powered by an efficient MoE architecture. Easily test them out with the new Hugging Face demo.
 DeepSeek-VL2 gallery image
 DeepSeek-VL2 gallery image
 DeepSeek-VL2 gallery image
Launch Team
Eney
EneyProactive AI for Mac. Free test, 20,000 credits.
Promoted