How to Use olmOCR GGUF Model with Ollama?

#2
by koala8104 - opened

Hi,

I've downloaded the olmOCR GGUF model and added it to Ollama (running on localhost:11434), but I'm struggling to get it working properly.

Could someone share:

  1. The correct prompt format for olmOCR with Ollama
  2. How to convert PDFs to images and send them to the model
  3. A simple code example showing how to use it

I've read the GitHub repo but still haven't managed to make it work.

Thanks!

Sign up or log in to comment