Learn about parameter-efficient fine-tuning techniques with a focus on (Q)LoRA in this 48-minute lecture from UofU Data Science. Explore the principles and implementation of Low-Rank Adaptation (LoRA) and its quantized variant (QLoRA), understanding how these methods enable efficient model adaptation while maintaining performance. Dive into practical applications and methodologies for optimizing large language models with minimal computational resources, accompanied by comprehensive slides that illustrate key concepts and technical implementations.
Parameter-Efficient Finetuning - QLoRA and LoRA Methods
Overview
Syllabus
Parameter-efficient finetuning: (Q)LoRA
Taught by
UofU Data Science
Related Courses
-
Fine-Tuning LLM Models - Generative AI Course
-
Improving Accuracy of LLM Applications
-
LoRA: Low-Rank Adaptation for Parameter-Efficient Large Language Model Fine-Tuning
-
Very Few Parameter Fine-Tuning with ReFT and LoRA
-
Spectral Analysis of LoRA vs Full Fine-Tuning in Language Models
-
Optimizing LLM Fine-Tuning with PEFT and LoRA Adapter-Tuning for GPU Performance
