Using Lightweight AI with Small Language Models

Large language models like GPT, Llama, and Gemini are powerful, but that power comes at the cost of speed, efficiency, and compute power. For many AI applications and tasks, smaller, more efficient, and more specialized models can perform to the same level as LLMs with higher speed, less power, and less cost. In this course, learn what lightweight AI models are, when to use them, and how these models will figure into the future of AI. Instructor Morten Rand-Hendriksen also shares a quick demo of how to get started with Phi-3, a family of small-language models from Microsoft.

Learning objectives
Comprehend the difference between a lightweight and a large language model
Awareness of when to use a lightweight model over an LLM
Ability to deploy and work with a lightweight model in Azure
Know when and why to bring a lightweight model into consideration