Beginner’s Visual Guide to Quantisation Methods for LLMs

Author(s): Parth Chokhra

Originally published on Towards AI.

A Visual Step-by-Step Guide to Popular Quantisation Techniques

Quantisation is the process of reducing the precision of numbers used in a model; for example, storing weights in 8-bit integers instead of 16- or 32-bit floats. This makes models smaller, faster, and more efficient to run, often with only a small drop in accuracy. For large language models, quantisation is especially important because of their size and hardware demands. To understand this, look at the example below.

This article explores various quantisation methods for large language models, focusing on two main approaches: Quantisation Aware Training (QAT) and Post-Training Quantisation (PTQ). The author discusses different algorithms and techniques associated with these methods, highlighting their trade-offs in accuracy and speed. The article also addresses the implications of these methods for deployment and provides insights on how to choose the best approach based on specific use cases.

Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI