NEWAgents can now see video via MCP.Try it now →
    Models/Image To Text/sbintuitions/sarashina2.2-ocr
    Image To Texttransformersmit

    sarashina2.2-ocr

    by sbintuitions

    Identifier
    Model ID
    sbintuitions/sarashina2.2-ocr

    Tags

    transformerssafetensorssarashina2_visiontext-generationmultimodalocrdocument-understandingvision-languageimage-to-textcustom_codejaenarxiv:2503.09208base_model:sbintuitions/sarashina2.2-3b-instruct-v0.1base_model:finetune:sbintuitions/sarashina2.2-3b-instruct-v0.1license:mitregion:us

    Use sarashina2.2-ocr 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