dots-studio / dots.ocr

Vision3B398.1K1.3KUpdated Oct 31, 2025

Downloads

398.1K

Likes

1.3K

Last updated

Oct 31, 2025

License

mit

dots.ocr is a powerful, multilingual document parser that unifies layout detection and content recognition within a single vision-language model while maintaining good reading order. Despite its compact 1.7B-parameter LLM foundation, it achieves state-of-the-art(SOTA) performa…

Tasks & library

  • image text to text
  • dots_ocr

Tags

  • dots_ocr
  • text-generation
  • image-to-text
  • ocr
  • document-parse
  • layout

Technical specifications

Parameters3B
Librarydots_ocr
Languagesen, zh, multilingual
Licensemit