Build Your Own AI Lab

• Instruction on set up and optimization of AI labs to research and experiment in a secure environment
• Emphasis on real-world applications, hands-on projects, and case studies that allow you to apply learned concepts directly
• Focus on open-source large language models (LLMs) and generative AI

In this course, you will learn how to create powerful and secure AI research environments. The course covers both home-based and cloud-based AI labs, offering comprehensive guidance on hardware and software setup, security best practices, cost management, and scalability. You will learn how to integrate and leverage the strengths of both environments, ensuring they have the flexibility to meet diverse research needs. You will also learn how to run open-source models that can be accessed at Hugging Face, such as Llama 3, Phi 3, Mistral, Gemma, and other models. Omar Santos will provide demonstrations on how to build a system at home that can run these models. You will learn how to use Ollama to run these models easily in your home. The course also covers an overview of Amazon Bedrock, Amazon SageMaker, Google Vertex AI, and Microsoft Azure Cognitive Services. It also covers advanced topics such as high-performance computing and edge AI, making it a well-rounded educational experience for anyone looking to advance their AI research and experimentation.

Generative AI models are rapidly advancing, and small language models (SLMs) are becoming highly efficient. This is offering powerful capabilities with reduced computational resources, making AI more accessible and scalable. This course is essential for anyone learning Generative AI, LLMs, and SLMs because it addresses the practical challenges and opportunities of setting up and managing AI labs in today's dynamic technological landscape.