Large Language Models Demystified
This course program introduces learners to the intricacies of building large language models (LLMs). It aims to teach learners the process of building models from scratch to help understand the black-box that is LLMs. The course series breaks down the components of transformers, their attention mechanisms, and how they have revolutionized natural language processing (NLP) tasks. The courses focuses on a state-of-the-art LLM architecture and the processing and training involved to deploy the model. By the end of this series, learners will have a comprehensive understanding of LLM construction and the principles behind transformers, empowering them to apply these models in real-world applications.
What you will learn:
- Practical applications and impact of LLMs in real-world scenarios
- The transformer model and attention mechanisms
- Coding transformer layers and attention mechanisms from scratch
- Best practices for dataset selection and preprocessing in LLM training
- Pre-training and fine-tuning paradigms in LLM development
- Evaluating model performance, including common debugging techniques
- Hands-on exercises for e2e model development, training, and deployment
Courses included in this program:
Course Program Length: 5 hours
Who Should Attend: AI Researchers and Academics, Data Scientists, Educators and Instructors, Enthusiasts with a Strong Programming Background, Machine Learning Engineers, Software Developers and Programmers, Students (experience in linear algebra and calculus required), Technical Professionals in industry, Technical Product Managers and Tech Leads
Instructors
Sai Chand Boyapati, Director of Software Quality Assurance
Hamza Mohammed, Machine Learning Engineer, Samsung Research America
Publication Year: 2026
ISBN: 978-1-7281-7891-2