-
Notifications
You must be signed in to change notification settings - Fork 1.6k
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
[Feature] Add Quantization Support for VeRA Method #2070
Comments
Thanks a lot @ZiadHelal for offering to work on this feature. Please go ahead and submit a PR. You can also create a draft PR that does not yet cover all your points, and I can give early feedback, which is often better than trying to finish everything in one step. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Feature request
This pull request aims to introduce support for quantization in the VeRA PEFT method. This enhancement is in response to the issue #1921, which highlighted the need for compatibility between VeRA and quantized models.
Motivation
The motivation behind this feature request is to extend the functionality of the VeRA method to support models that have been quantized using techniques such as bitsandbytes. Currently, users face issues with dimension mismatches and incorrect tensor shapes when applying VeRA to quantized models. By adding support for quantization, we can improve the usability and flexibility of VeRA, making it a more powerful tool for a broader range of use cases.
Your contribution
I am willing to submit a pull request with the implementation of this feature. The PR will include:
Please let me know if there are any additional requirements or considerations for this feature. I look forward to contributing this enhancement to the project and am open to any feedback or suggestions. @BenjaminBossan
The text was updated successfully, but these errors were encountered: