Explore parameter efficient fine-tuning (PEFT) in natural language processing and generative AI through this 23-minute video. Learn about the evolution from RNNs to transformers, the challenges of large language models, and various PEFT techniques like additive adapters, prefix-tuning, LoRA, and QLoRA. Gain insights into the importance of PEFT in addressing the computational demands of modern NLP models. Discover how these techniques are applied in popular LLMs like Llama. Follow along with three comprehensive passes, interspersed with quizzes, to deepen your understanding of PEFT's concepts, implementation details, and performance evaluation.
Overview
Syllabus
Introduction
Pass 1: What & Why PEFT
Quiz 1
Pass 2: Details
Quiz 2
Pass 3: Performance Evaluation
Quiz 3
Summary
Taught by
CodeEmporium
Related Courses
-
Fine-Tuning LLM Models - Generative AI Course
-
Improving Accuracy of LLM Applications
-
H2O ai Large Language Models (LLMs) - Level 2
-
Large Language Models: Foundation Models from the Ground Up
-
LLMs Mastery: Complete Guide to Transformers & Generative AI
-
Parameter Efficient Fine-Tuning with Multiple LoRA Adapters for Large Language Models
