hugpadhugpad

ATH-MaaS / OvisOCR

Vision1.4B85718Updated Oct 22, 2026
Hugging Face

Downloads

857

Likes

18

Last updated

Oct 22, 2026

License

apache-2.0

We introduce OvisOCR, a lightweight end-to-end multimodal large language model (MLLM) tailored for high-fidelity document parsing. Unlike conventional Crop-OCR-Merge systems that rely on layout detection, localized cropping, specialized recognizers, and heuristic merging, Ovis…

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • ovis2_6
  • text-generation
  • ocr
  • document-parsing
  • document-understanding

Technical specifications

Parameters1.4B
Librarytransformers
LanguagesNot available
Licenseapache-2.0