Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

(draft) colpali WIP #394

Open
wants to merge 29 commits into
base: main
Choose a base branch
from
Open

(draft) colpali WIP #394

wants to merge 29 commits into from

Conversation

I8dNLo
Copy link
Contributor

@I8dNLo I8dNLo commented Nov 8, 2024

Colpali draft
Works for texts, does not work for images

@I8dNLo I8dNLo requested a review from joein November 20, 2024 15:46
fastembed/text/colpali_model.py Outdated Show resolved Hide resolved
fastembed/text/colpali_model.py Outdated Show resolved Hide resolved
fastembed/image/colpali_model.py Outdated Show resolved Hide resolved
fastembed/image/colpali_model.py Outdated Show resolved Hide resolved
@joein joein self-requested a review November 22, 2024 08:14
fastembed/image/colpali_model.py Outdated Show resolved Hide resolved
fastembed/image/image_embedding.py Outdated Show resolved Hide resolved
fastembed/text/colpali_model.py Outdated Show resolved Hide resolved
fastembed/text/colpali_model.py Outdated Show resolved Hide resolved

supported_onnx_models = [
{
"model": "akshayballal/colpali-v1.2-merged",
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can we use only text part of the model here?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It's not really separated in our quantization. We could re-quantize it and separate, but I can not say it will have original behaviour. It could, but I'm not sure 100%

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Which image model is used?
How much does it weight?
Does it make sense to split the models or the difference is negligible?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Gemma 2B

fastembed/image/colpali_model.py Outdated Show resolved Hide resolved
fastembed/text/colpali_model.py Outdated Show resolved Hide resolved
@qdrant qdrant deleted a comment from review-notebook-app bot Nov 29, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants