Efficient Fine-Tuning of LLMs with LoRA
With the advent of tools from Hugging Face like the Parameter Efficient Fine-Tuning (PEFT) library, it has never been easier to customize LLMs for downstream tasks. PEFT methods fine-tune a small number of parameters while freezing most of the neural network weights that define an off-the-shelf LLM.
The first method released for fine-tuning via PEFT and the most popular method used in the industry today is Low-Rank Adaptation of Large Language Models (LoRA), which combines clever matrix algebra with a singular focus on training only the Transformer attention blocks.
In this event, we’ll dig into the core concepts that allow us to efficiently fine-tune LLMs with PEFT and break down the LoRA approach from first principles. We will show how LoRA reduces the number of trainable parameters by many orders of magnitude while avoiding increased inference latency and producing high-performance results.
By the end of the session, you’ll have a deep intuition about why and how LoRA works so well, and you’ll also learn all relevant PEFT-LoRA implementation details in Python, from initialization to configuration to downstream-task training.
Join us live to learn:
How to fine-tune LLMs with open-source tooling
The concepts behind Hugging Face’s PEFT-LoRA
To adapt pre-trained LLMs to downstream tasks
Speakers:
Dr. Greg Loughnane is the Founder & CEO of AI Makerspace, where he serves as an instructor for their LLM Engineering and LLM Ops: LLMs in Production courses. Since 2021 he has built and led industry-leading Machine Learning & AI boot camp programs. Previously, he worked as an AI product manager, a university professor teaching AI, an AI consultant and startup advisor, and ML researcher. He loves trail running and is based in Dayton, Ohio.
Chris Alexiuk, is the Co-Founder & CTO at AI Makerspace, where he serves as an instructor for their LLM Engineering and LLM Ops: LLMs in Production courses. A former Data Scientist, he also works as the Founding Machine Learning Engineer at Ox. As an experienced online instructor, curriculum developer, and YouTube creator, he’s always learning, building, shipping, and sharing his work! He loves Dungeons & Dragons and is based in Toronto, Canada.