High mileage of Low Rank Adapters by Shikhar Chauhan

Low Rank Adapters (LoRA) are transforming how large AI models are fine-tuned and deployed. In this talk, Shikhar Chauhan explores the foundations of LoRA, covering its mathematical principles, implementation with Hugging Face and PEFT, and the practical advantages it brings to modern AI workflows. This session demonstrates how LoRA enables faster training, smaller model sizes, scalable deployments, and reduced catastrophic forgetting. Through hands-on examples, viewers will learn how to fine-tune language and document AI models, use adapter ensembles, and address real-world challenges such as expired GDPR consent in datasets. :::::: If you love watching content like this, consider joining us in person at the next event: www.datamakersfest.com 👉 FOLLOW US Instagram:   / datamakersfest   LinkedIn:   / data-makers-fest   Our channel features talks for anyone building products and services with and around data. Subscribe to our channel for videos on Data Science, Machine Learning, AI, Data Engineering, and more. Data Makers Fest videos may be used for non-commercial purposes under a Creative Commons License, Attribution–Non-Commercial–No Derivatives (or the CC BY – NC – ND 4.0 International). To use the talk for other purposes, please contact us at [email protected]. #datamakersfest #datascience #ai #machinelearning #dataengineering