vanilla-llama VS LLaMA-Factory

I shouldn't have any trouble with the second step, but I'm not sure how to get started on the first one. I found a Python package for interfacing with LLaMA, but its examples focus on just generating text, and I'm not sure how I would actually get embedding vectors or anything beyond text generation. Ideally, I would like to not even just create embedding vectors but rather directly hook up some new layers to LLaMA for supervised learning.

Depends what model you want to train, and how well you want your computer to keep working while you're doing it.

If you're interested in large language models there's a table of vram requirements for fine-tuning at [1] which says you could do the most basic type of fine-tuning on a 7B parameter model with 8GB VRAM.

You'll find that training takes quite a long time, and as a lot of the GPU power is going on training, your computer's responsiveness will suffer - even basic things like scrolling in your web browser or changing tabs uses the GPU, after all.

Spend a bit more and you'll probably have a better time.

[1] https://github.com/hiyouga/LLaMA-Factory?tab=readme-ov-file#...