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.

Sign up for GitHub

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

Jump to bottom

Load existing lora adapter not trained using mlx-vlm #140

Open

Benjoyo opened this issue Dec 4, 2024 · 1 comment

Benjoyo commented Dec 4, 2024 •

edited

Loading

How would I go about converting and loading a lora adapter (say, https://huggingface.co/lightonai/MonoQwen2-VL-v0.1) that wasn't trained using mlx-vlm?

It seems not only the weights probably have the wrong format but also the adapter_config.json is different?

Can you give some pointers? Thanks!

Owner

Blaizzy commented Dec 21, 2024

Thanks for bringing this up!

I think that for now you cna programmatically change the adapter config and LORA settings to work here too.

We are due to a refactoring here so you can easily use external adapters and more. I will work on it but appreaciate any help :)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment