-
Notifications
You must be signed in to change notification settings - Fork 111
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
base: main
Are you sure you want to change the base?
(draft) colpali WIP #394
Conversation
fastembed/text/colpali_model.py
Outdated
|
||
supported_onnx_models = [ | ||
{ | ||
"model": "akshayballal/colpali-v1.2-merged", |
There was a problem hiding this comment.
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?
There was a problem hiding this comment.
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%
There was a problem hiding this comment.
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?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Gemma 2B
# Conflicts: # fastembed/late_interaction/colpali.py
Colpali draft
Works for texts, does not work for images