Explore AI Model Architectures

🛠 Lab from the AI Platform Engineering Bootcamp. Used in Week 1. Bootcamp landing page: https://academy.tekanaid.com/bootcamps/ai-platform-engineering-bootcamp Parent course(s):

• Week 1: AI Foundations for Infrastructure Engineers (slug: ai-foundations-101)

🟡 Beta bootcamp lab. Hands-on instructions, check scripts, and solve scripts are in place. Lab is part of the running Platform Assistant capstone arc that grows across all 8 weeks of the bootcamp.

In this lab, you'll explore the practical aspects of AI models from an infrastructure perspective.

You'll learn to:

• Understand different model formats (GGUF, SafeTensors) and when to use each
• Pull and inspect model metadata to understand resource requirements
• Compare inference speeds across different model sizes
• Make informed decisions about model selection for your infrastructure

Prerequisites:

• Basic Linux command line skills
• Understanding of system resources (memory, CPU)

Key Concepts:

• Model quantization levels (FP16, INT8, INT4)
• VRAM and RAM requirements
• Inference latency vs model capability tradeoffs