Learn about LoftQ (LoRA-Fine-Tuning-aware Quantization), a groundbreaking LLM quantization method developed by GeorgiaTech and Microsoft researchers, in this 14-minute technical video. Explore the theoretical foundations of combining quantization with Low Rank Adaptations (LoRA) of high-precision weight tensors, presented in an accessible manner. Delve into the optimization problem, loss function, and understand why this innovative approach surpasses QLoRA in performance. Master the core concepts behind this memory-efficient AI technology through a structured breakdown of the research paper's key findings and methodologies.
Overview
Syllabus
Intro
LoftQ
Publication
Main Idea
Optimization Problem
Why LoftQ
Loss Function
Conclusion
Taught by
Discover AI
Related Courses
-
Fine-Tuning LLM Models - Generative AI Course
-
H2O ai Large Language Models (LLMs) - Level 2
-
Generative AI Advance Fine-Tuning for LLMs
-
Efficiently Serving LLMs
-
Understanding 4-bit Quantization and QLoRA - Memory Efficient Fine-tuning of LLMs
-
Optimizing LLM Fine-Tuning with PEFT and LoRA Adapter-Tuning for GPU Performance
