allenai

/

olmOCR-7B-0225-preview

like 503

Follow

Ai2 2.75k

I see the following requirements:

1. This model expects as input a single document image, rendered such that the longest dimension is 1024 pixels.
2. The prompt must then contain the additional metadata from the document.

My questions:

1. Is is really needed that the longest dimension is 1024 pixels? What happens if it's not?
2. Why is this needed? And what exact additional metadata is mandatory and useful?