Skip to content
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.

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

TinyLlama LoRA Example #138

Open
fakerybakery opened this issue Dec 18, 2023 · 6 comments
Open

TinyLlama LoRA Example #138

fakerybakery opened this issue Dec 18, 2023 · 6 comments
Labels
enhancement New feature or request

Comments

@fakerybakery
Copy link

Hi,
I saw this example and was wondering if it might be possible to train TinyLlama with LoRA. I haven't been able to figure out how to convert the weights.
Might it be possible to provide an example?
Thank you!
cc: @awni

@awni
Copy link
Member

awni commented Dec 18, 2023

It's a great idea, we'd love to extend the LoRA example to more models. You can see how we convert TinyLlama here

@awni awni added the enhancement New feature or request label Dec 18, 2023
@fakerybakery
Copy link
Author

fakerybakery commented Dec 18, 2023

Ah, nice - before I was trying to convert it with the Phi script :). So does LoRA w/ MLX supports TinyLlama?

@awni
Copy link
Member

awni commented Dec 18, 2023

There are a couple things missing in the LoRA example to work with TinyLlama (namely RoPE without traditional).

@fakerybakery
Copy link
Author

Hi,
Thank you so much! Is there a timeline for adding LoRA support for TinyLlama, now that the 3T version is released?
Thank you!

@awni
Copy link
Member

awni commented Jan 1, 2024

I got it working yesterday by using the conversion script in the llama example with a couple of small changes in the lora example. I think it makes sense to update the lora example to support downloading HF models directly. I can't give an exact ETA yet, but shouldn't take that long to implement.

@fakerybakery
Copy link
Author

Thanks! Also is there a way to convert MLX -> HF?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants