Projects
Assignments
Overview
This course introduces learners to the fundamentals of working with Granite family large language models (LLMs) using Red Hat Enterprise Linux AI. It focuses on the secure, enterprise-grade development, fine-tuning, deployment, and serving of generative AI models tailored to real-world business needs.
Objectives
At the end of Red Hat System Administration II training course, participants will be able to
Prerequisites
- Basic understanding of AI and ML concepts (recommended)
- Familiarity with the Linux command line
- Access to a RHEL AI machine (for BYOD participants; GPU not required for core labs)
Course Outline
Module 1: Generative AI Fundamentalskeerti2025-07-03T09:35:24+05:30
- Define generative AI: capabilities, benefits, and challenges
- Select appropriate models and techniques based on use cases
Module 2: Granite Models for Enterprise AIkeerti2025-07-03T09:45:54+05:30
- Understand Granite models
- Compare with larger, closed-source models
- Assess enterprise applicability
Module 3: Training Large Language Models with Red Hat Enterprise Linux AIkeerti2025-07-03T09:46:58+05:30
- Enable technical/non-technical collaboration
- Train and fine-tune LLMs using Red Hat Enterprise Linux AI and IBM Granite
Module 4: Deploying Trained Models with Red Hat Enterprise Linux AIkeerti2025-07-03T09:47:51+05:30
- Deploy and serve AI models
- Operate and manage models in production environments
