QLoRA — How to Fine-Tune an LLM on a Single GPU

An introduction with Python example code (ft. Mistral-7b)

This article is part of a larger series on using large language models (LLMs) in practice. In the previous post, we saw how to fine-tune an LLM using OpenAI. The main limitation to this approach, however, is that OpenAI’s models are concealed behind their API, which limits what and how we can build with them. Here, I’ll discuss an alternative way to fine-tune an LLM using open-source models and QLoRA.