NEWManaged multimodal retrieval.Explore platform →
    Models/Embeddings/vidore/colqwen2.5-v0.2
    HFVisual Embeddings

    colqwen2.5-v0.2

    by vidore

    36Kdl/month
    HuggingFaceUse in Pipeline
    Identifiers
    Model ID
    vidore/colqwen2.5-v0.2
    Feature URI
    mixpeek://image_extractor@v1/vidore_colqwen25_v1

    Specification

    FrameworkHF
    Organizationvidore
    FeatureVisual Embeddings
    Output768-dim vector
    Modalitiesvideo, image
    RetrieverVector Search
    Downloads/mo36K

    Build a pipeline with colqwen2.5-v0.2

    Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

    Open Studio

    Alternative Models

    openai/clip-vit-large-patch14
    Visual Embeddings
    google/siglip-base-patch16-224
    Visual Embeddings
    google/siglip2-giant-opt-patch16-384
    Visual Embeddings
    facebook/dinov2-large
    Visual Embeddings

    Related in Embeddings

    laion/clap-htsat-fused
    Audio Embeddings
    facebook/encodec_24khz
    Audio Embeddings
    BAAI/bge-large-en-v1.5
    Text Embeddings
    sentence-transformers/all-MiniLM-L6-v2
    Text Embeddings