Prince Canuma comments

Results 572 comments of


                                            Prince Canuma

Inaccurate Coordinate Outputs for MLX-Quantized UI-TARS-1.5 (4bit/6bit)

Awesome, feel free to ping me when it ready! I also left a comment on your current PR.

Load existing lora adapter not trained using mlx-vlm

Hey @Benjoyo 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...

Load existing lora adapter not trained using mlx-vlm

Closing stale We are solving this in #499

feat(build): migrate to `pyproject.toml`

Hey @SauravMaheshkar Thanks for the PR! I have one question, why move to pyproject.toml? what are the benefits?

feat(build): migrate to `pyproject.toml`

Perfect, thanks @SauravMaheshkar! Let me research, test it out and give it some thought :)

feat(build): migrate to `pyproject.toml`

Thanks a lot @SauravMaheshkar! We are proceeding with this change! I will look into it and merge it tomorrow 👌🏽

feat(build): migrate to `pyproject.toml`

Thank you very much @SauravMaheshkar!

feat(build): migrate to `pyproject.toml`

Please resolve the conflicts and will be merge today @SauravMaheshkar!

feat(build): migrate to `pyproject.toml`

Could you run > pre-commit run --all

Repeated model download despite presence in Hugging Face cache

Hey @NiltonVolpato Thanks for raising the issue! No worries, feel free to raise any concerns at anytime.