docling-project / docling-project/docling
I was trying to experiment with different page_batch_size and for 16 it loading 5 gb model and for page_batch__size 12 it is loading 4gb model and for batch_size =2 it is loading 1gb model why is this happening
Open
question
- Dominant language
- Python
- Stars
- 66.4k
- Forks
- 4.8k
- Avg merge
- 2d 21h
- Merged PRs (30d)
- 84
Description
what is the reason behind it and is this behaviour expected and why am i not seeing an improvement of speed of parsing even if i changed the page_batch_size from 2 to 16
Contributor guide
Assessment
This issue has not been assessed yet.