Prince Canuma comments

Results 572 comments of


                                            Prince Canuma

Add Support for OS-Copilot/OS-Atlas-Base-7B

Hey Prince I have my plate full, I have given you all the pointers you need. This is a great opportunity for you to learn. From the images you shown...

Add Support for OS-Copilot/OS-Atlas-Base-7B

I'm closing this issue for now. Please feel free to re-open if and when you found a bug/problem with MLX that is reproducible.

Errors when running example script

Hey @DePasqualeOrg I managed to replicate the issue and will fix it in #67 Yesterday, I accidentally introduced a bug on v0.0.14 and v0.0.15.

Errors when running example script

This template issue is being cause by transformers :(

Errors when running example script

I have to reupload all models again. They moved the templates to the preprocessor config file.

[Tentative] Trivial addition of the OpenAI URL.

Hey @Narsil This is awesome! Can we make it a bit more general for all TTS models

[Tentative] Trivial addition of the OpenAI URL.

Hey guys Does this PR #153 solve it?

Does MLX-VLM support fine-tuning of vision tower layers?

Hey @sachinraja13 My pleasure, it means a lot! Not yet, but we will add it along side the projector. Right now, @Goekdeniz-Guelmez is actively working on doing an overhaul on...

Does MLX-VLM support fine-tuning of vision tower layers?

Yes, you could do that. You would then train a vision adapter that would need to load.

Does MLX-VLM support fine-tuning of vision tower layers?

My pleasure :) It won't be long now