hugpadhugpad

ATH-MaaS / OvisOCR2

Vision853M81.5K506Updated Oct 22, 2026
Hugging Face

Downloads

81.5K

Likes

506

Last updated

Oct 22, 2026

License

apache-2.0

We are pleased to announce the release of OvisOCR2, a compact 0.8B end-to-end model for page-level document parsing. Given a document page image, OvisOCR2 generates a Markdown representation in natural reading order, covering text, formulas, tables, and visual regions.

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • qwen3_5
  • image-text-to-text
  • ocr
  • document-parsing
  • multimodal

Technical specifications

Parameters853M
Librarytransformers
LanguagesNot available
Base modelQwen/Qwen3.5-0.8B
Licenseapache-2.0