Getting Started with Llama and Other Local Models
Published by O'Reilly Media, Inc.
Querying your local files privately with Llama 3
Course outcomes
- Develop a basic understanding of the Llama 3 architecture
- Learn to download, install, and run Llama 3 models (7B, 13B and 70B models)
- Understand the relevance of open source LLMs, benefits and risks
- Understand how to develop simple text-based applications using Llama 3
- Understand how to query personal documents privately using Llama 3
- Learn the basics of fine-tuning Llama 3 LLMs
Join expert Lucas Soares to get a solid introduction to Llama 3, the cutting-edge open source large language model developed and released by Meta. You’ll set up, download, and install Llama 3 and learn to run inference with your personal LLM hosted on your local machine. You’ll get hands-on to build simple text-based applications using Llama 3-based LLMs, including an app to query your own PDF documents privately. By the end of this four-hour course, you’ll be equipped to query your own documents, set up a simple LLM assistant locally, and build private LLM-based applications with Llama 3.
What you’ll learn and how you can apply it
- Query your own PDF documents using Llama 3
- Set up a simple and free LLM assistant on a local machine
- Build simple and private LLM-based applications with Llama 3 locally
This live event is for you because...
- You’re an AI/software engineer or developer.
- You’re a data scientist or machine learning engineer.
- You’re interested in learning about large language models, specifically ChatGPT, and how to build applications.
Prerequisites
- Familiarity with Python programming
- Some knowledge of machine learning concepts
- Basic understanding of natural language processing
Recommended preparation:
- Read chapters 1, 6, and 7 in Natural Language Processing with Transformers (book)
Recommended follow-up:
- Read _Language Models in Plain English _(report)
- Read Developing Apps with GPT-4 and ChatGPT (book)
- Read Generative AI on AWS (book)
- Read Hands-On Large Language Models (book)
Schedule
The time frames are only estimates and may vary according to how the class is progressing.
Basics of large language models and their applications (85 minutes)
- Presentation: Introduction to large language models and their applications; getting started with Llama 3 (open source LLMs and setup)
- Hands-on exercise: Set up Llama 3 and run inference locally with Llama3.2-3B
- Q&A
- Break
Querying documents locally (70 minutes)
- Presentation: Text summarization with Llama 3.2; building a private Q&A system for PDFs
- Hands-on exercises: Build a simple text summarizer; build a Q&A for private docs
- Q&A
- Break
Querying local files privately (55 minutes)
- Presentation: Introduction to fine-tuning approaches with Llama 3 models
- Hands-on exercise: Explore fine-tuning options for Llama 3.1 and 3.2: explore LoRa
- Q&A
Your Instructor
Lucas Soares
Lucas Soares is a machine learning engineer who has worked at K1 Digital and Biometrid, where he developed computer vision and NLP models for applications such as document verification, OCR-based applications, and recommender systems. Lucas has also developed various ML models, including neural networks, Siamese networks, convolutional neural networks, LSTMs, and genetic algorithms.