datalab-to / chandra-ocr-2

Vision5.3B1.4M596Updated Jun 26, 2026

Downloads

1.4M

Likes

596

Last updated

Jun 26, 2026

License

openrail

Chandra 2 is a state of the art OCR model from Datalab that outputs markdown, HTML, and JSON. It is highly accurate at extracting text from images and PDFs, while preserving layout information.

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • qwen3_5
  • image-text-to-text
  • ocr
  • pdf
  • markdown

Technical specifications

Parameters5.3B
Librarytransformers
LanguagesNot available
Licenseopenrail