Drew Thomasson
Drew Thomasson
Agreed I want llama 3 support as well
> Colab notebook: https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing OMG THANK YOU SO MUCH! Already fine tuning my own models with this colab
Just made a Audiobook Generator that uses Piper-tts, You can select from all the Available Piper tts voices in the gui. https://github.com/DrewThomasson/ebook2audiobookpiper-tts https://hub.docker.com/repository/docker/athomasson2/ebook2audiobookpiper-tts Has its own docker image and everything...
I'm pretty sure Ive gotten xtts to run on mps on my M1 pro, But I don't seem to see any speedup when I use it on mps anyway and...
very interesting... thats even weirder cause I barley see a change on my side lol
lol well now its not working on my computer but anyway ## but also related to your error of `The operator 'aten::_fft_r2c' is not currently implemented for the MPS device.`...
> @DrewThomasson Oh what's the inference commands you used - what `max_seq_length` was set and was the model finetuned? I was planning to add a flag to check if a...
ok yeah looks like that fixed now its outputting like this >>> hey what is up? thank you for coming to the office, and i hope your day was good...
# Colab Notebooks Encountering error with(IE All of them) Tinyllama Google Colab: [Tinyllama Notebook](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing#scrollTo=yqxqAZ7KJ4oL) Full Error Log ==((====))== Unsloth - 2x faster free finetuning | Num GPUs = 1 \\...