
Description
Converting complex PDFs to Markdown mangles multi-column layouts, cross-page tables and mixed content. OCRFlux is a lightweight yet powerful multimodal PDF-to-Markdown toolkit that excels at complex layouts.
It parses complicated tables and merges content across pages with a 3B model that runs on ordinary GPUs.
Layouts:Columns and figures.
Tables:Complex ones.
Cross-page:Merged content.
Lightweight:3B model.
It parses complicated tables and merges content across pages with a 3B model that runs on ordinary GPUs.
Features
Layouts:Columns and figures.
Tables:Complex ones.
Cross-page:Merged content.
Lightweight:3B model.
