DeepSeek-VL2

    MoE vision-language, now easier to access

    特集
    523 投票
     DeepSeek-VL2 media 1
     DeepSeek-VL2 media 2
     DeepSeek-VL2 media 3

    説明

    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.

    推奨製品