Prince Canuma comments

Results 572 comments of


                                            Prince Canuma

[Feature Request] Supports fine-tuning

Thanks @madroidmaq I'm working on it here: #41

[Feature Request] Supports fine-tuning

It should be available soon.

[Feature Request] Supports fine-tuning

you can read more about the supported models here: https://github.com/Blaizzy/mlx-vlm/blob/main/mlx_vlm/LORA.MD

Server shuts down randomly when sending texts.

Hi @jjboi8708 Yes, this will be fixed, From what I can telln you ran out of memory. Could you share your machine specs and the text you were processing so...

Remove scipy dependency

I agree with you! Could you send a PR and add some metrics like performance (acc and performance)?

Which specific models work with this framework?

@jrp2014 good question! In general you can find the correct models in the [mlx-community](https://huggingface.co/mlx-community) repo. They are usually converted and uploaded there before the release. We currently support the Pixtral...

Which specific models work with this framework?

Install from source. I recently merged a PR fixing all the bugs

Which specific models work with this framework?

``` pip install git+https://github.com/Blaizzy/mlx-vlm.git ```

Which specific models work with this framework?

Uninstall and reinstall from source. It seems you have an older version. Check the version you have installed.