This track equips you with the skills to implement Llama 3 for tasks ranging from running inference on pre-trained models to fine-tuning for custom use cases. Throughout the track, you’ll experiment using the open-source Llama model in various applications, including learning techniques to prepare your models for running on standard consumer hardware. You’ll explore tasks that Llama excels at, such as summarization and text generation, and get ready to integrate the open-source Llama models into your projects to improve efficiency. This track is ideal for AI and software professionals looking to use open-source models to innovate their current processes.
Overview
Syllabus
- Working with Llama 3
- Explore the latest techniques for running the Llama LLM locally and integrating it within your stack.
- Classifying Emails using Llama
- Fine-Tuning with Llama 3
- Fine-tune Llama for custom tasks using TorchTune, and learn techniques for efficient fine-tuning such as quantization.
Taught by
Imtihan Ahmed and Francesca Donadoni