Intro to Fine-Tuning Large Language Models

From the creator

Learn about fine-tuning large language models (LLMs). The course covers key methodologies, including supervised fine-tuning and reinforcement learning with human feedback (RLHF). It also introduces a technique called QLoRA, which enables you to fine-tune massive models like Llama 70B on a home workstation. The course guides you from theory to practical implementation using tools like Python, PyTorch, and Hugging Face. ✏️ Created by @LunarTech_ai ❤️ Try interactive AI courses we love, right in your browser: https://scrimba.com/freeCodeCamp-AI (Made possible by a grant from our friends at Scrimba) ⭐️ Contents ❤️ - 0:00:00 Course Overview - 0:00:15 What is Fine-Tuning and How is it Different? - 0:00:21 Hands-on Methodologies - 0:00:28 Deep Dive into Parameter Efficient Fine-Tuning - 0:00:36 Exploring QLoRA: A Revolutionary Method - 0:00:44 Practical Case Studies - 0:01:15 Instructor Introduction - 0:02:05 Course Outline (More Detail) - 0:02:30 Highlight of the Course: Parameter Efficient Fine-Tuning - 0:03:08 Who is this Course For? - 0:04:01 Module 1: Introduction to Fine-Tuning - 0:05:27 The Benefits of Fine-Tuning - 0:07:17 First Part: Fine-Tuning LLMs Module - 0:07:51 Fine-Tuning Allocation in LLM Life Cycle - 0:08:43 Pre-trained vs Fine-Tuned Model - 0:10:40 Understanding Shortcomings and Specialization - 0:11:00 Fine-Tuning Impact Example: Chatbot - 0:13:07 Formal Definition of Fine-Tuning - 0:18:53 Fine-Tuning Examples: Doctor and Lawyer - 0:26:08 Pre-Training vs. Fi

Published 2025-09-04 · Watch on YouTube ↗
Availability and playback restrictions are controlled by the original channel.