Fine-Tuning with Llama 3

Overview

Get Certified in Python, SQL & AI — 50% Off This May

690+ courses, career tracks, and industry-leading certifications trusted by 19M+ learners and 80% of the Fortune 1000.

Start Learning Today

Fine-tune Llama for custom tasks using TorchTune, and learn techniques for efficient fine-tuning such as quantization.

Fine-tuning the Llama model

This course provides a comprehensive guide to preparing and working with Llama models. Through hands-on examples and practical exercises, you'll learn how to configure various Llama fine-tuning tasks.

Prepare datasets for fine-tuning

Start by exploring dataset preparation techniques, including loading, splitting, and saving datasets using the Hugging Face Datasets library, ensuring high-quality data for your Llama projects.

Work with fine-tuning frameworks

Explore fine-tuning workflows using cutting-edge libraries such TorchTune and Hugging Face’s SFTTrainer. You'll learn how to configure fine-tuning recipes, set up training arguments, and utilize efficient techniques like LoRA (Low-Rank Adaptation) and quantization using BitsAndBytes to optimize resource usage. By combining techniques learned throughout the course, you’ll be able to customize Llama models to suit your projects' needs in an efficient way.

Syllabus

Preparing for Llama fine-tuning

Explore options for fine-tuning Llama 3 models and dive into TorchTune, a library built to simplify fine-tuning. This chapter guides you through data preparation, TorchTune's recipe-based system, and efficient task configuration, providing the key steps to launch your first fine-tuning task.

Fine-tuning with SFTTrainer on Hugging Face

Learn how fine-tuning can significantly improve the performance of smaller models for specific tasks. Start with fine-tuning smaller Llama models to enhance their task-specific capabilities. Next, discover parameter-efficient fine-tuning techniques such as LoRA, and explore quantization to load and use even larger models.