Deepseek-VL2

Deepseek-VL2

MoE Vision-Language, Now Easier to Access

5.0
1 review

586 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.

No makers yet

It looks like there are no makers for this product.