NEWAgents can now see video via MCP.Try it now →
    Models/Image Text To Text/microsoft/kosmos-2.5
    Image Text To Texttransformersmit

    kosmos-2.5

    by microsoft

    90Kdl/month
    270likes
    HuggingFaceUse in Pipeline
    Identifier
    Model ID
    microsoft/kosmos-2.5

    Tags

    transformerssafetensorskosmos-2.5image-text-to-textenarxiv:2309.11419license:mitendpoints_compatibleregion:us

    Use kosmos-2.5 on Mixpeek

    Build multimodal processing pipelines with this model and others. Extract features, run inference, and set up retrieval, all through the Mixpeek pipeline builder.

    Open Pipeline Builder

    Specification

    Organizationmicrosoft
    TaskImage Text To Text
    Librarytransformers
    Licensemit
    Downloads/mo90K
    Likes270

    View on HuggingFace

    See model card, files, and community discussion

    Related Image Text To Text Models

    Qwen/Qwen3-VL-2B-Instruct
    126.9M
    Qwen/Qwen2.5-VL-7B-Instruct
    8.9M
    Qwen/Qwen3.5-9B
    7.1M
    google/gemma-4-31B-it
    5.8M
    moonshotai/Kimi-K2.5
    4.7M
    Qwen/Qwen2.5-VL-3B-Instruct
    4.3M
    google/gemma-4-26B-A4B-it
    4.2M
    Qwen/Qwen3-VL-8B-Instruct
    4.0M