LoRA and QLoRA: the math, rank selection and practice

LoRA is the technique that democratised LLM fine-tuning. Before it, fine-tuning a 7B model required ~112 GB of GPU memory — 14 A100s. With QLoRA, the same job fits on a single 24 GB consumer GPU. This lesson explains the mathematical trick that makes this possible, how to choose the key hyperparameter (rank), and how to run it in practice.

Full content is available with a subscription.
Get full access to all courses on the platform for one year with a single payment.
Unlike other platforms that charge per course, here you get everything for one price, and after one year of use there will be no automatic charge for the following year.