allenai/olmocr
Turns PDFs and scanned or image-only documents into clean markdown. It runs a 7B vision-language model, so it keeps tables, equations, handwriting and multi-column layouts, and it drops repeated headers and footers.
Idea adaptedKey files read, not run
I learnt this repo's idea and adapted it into my own workspace setup.
How we know
We read the README and key files, not every source file, and did not run it, so the most we can say is Idea adapted or Risky.
Good for
Anyone with a pile of PDFs or scans who needs searchable text, or clean document data for training a language model.
Not for
Machines without a capable GPU, since a 7B vision model is heavy to run, and anyone who only needs quick plain-text extraction from simple PDFs.
Repo
- Stars
- None
- License
- NoneNo license means the author keeps every right. You can read the code, but you have no right to copy or reuse it.
- Maturity
- active
- Last push
- Last checked
- 2026-11-14