mlx-vlm icon indicating copy to clipboard operation
mlx-vlm copied to clipboard

Published 20 hours ago • verified publisher icon Blaizzy

Load existing lora adapter not trained using mlx-vlm

Open Benjoyo opened this issue 10 months ago • 1 comments

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!

Benjoyo avatar Dec 04 '24 15:12 Benjoyo