On: A simple guide to fine-tuning Llama 2

[treprinum]

I understand, I use llama.cpp for my own personal stuff but can't override the policy on the project I want to plug it in, which is python-only.

[pests → treprinum]

There was a post yesterday about a 500 line single-file C implmenetation of llama2 with no dependencies. The llama2 architecture is hard coded. It shouldn't be too hard to port to python.

Found the repo, couldn't easily find the HN thread.

https://github.com/karpathy/llama2.c

[treprinum → pests]

That's Andrej's toy project, it won't run 7B LLaMA.

[NateGenX → treprinum]

It does now: https://github.com/karpathy/llama2.c#metas-llama-2-models