A beginner-friendly guide to Generative AI and LLMs covering transformer basics, and hands-on python labs
This course offers a hands-on, beginner-friendly introduction to Generative AI and Large Language Models (LLMs). From foundational machine learning concepts to real-world NLP applications, learners will gain both theoretical knowledge and practical experience using Python and Hugging Face.
What you’ll learn
- Understand the Fundamentals of Machine Learning and Generative AI.
- Gain Practical Knowledge of Large Language Models (LLMs).
- Perform Hands-on Tasks Using Python and Hugging Face.
- Evaluate and Tune LLM Outputs Effectively.
Course Content
- Introduction –> 2 lectures • 17min.
- Introduction to Generative AI –> 6 lectures • 37min.
- Introduction to Large Language Models –> 5 lectures • 16min.
- Core Architecture of LLM and Neural Networks Basics –> 6 lectures • 1hr 6min.
- Transformers and Core Mechanisms –> 6 lectures • 1hr 10min.
- Practical Applications and Labs –> 5 lectures • 41min.
- Evaluation and Advanced Concepts –> 3 lectures • 27min.
- Final Test –> 0 lectures • 0min.
Requirements
This course offers a hands-on, beginner-friendly introduction to Generative AI and Large Language Models (LLMs). From foundational machine learning concepts to real-world NLP applications, learners will gain both theoretical knowledge and practical experience using Python and Hugging Face.
By the end of the course, you will understand how LLMs work, how they are built, and how to apply them to real-world problems like chatbots, sentiment analysis, and translation.
What You’ll Learn:
- Foundations of Machine Learning (ML) and Generative AI
- What is ML with real-world examples
- Generative vs Discriminative AI
- Basic probability concepts and Bayes’ theorem
- Case studies in digit recognition
- Introduction to Large Language Models (LLMs)
- What LLMs are and what they can do
- Real-world applications of LLMs
- Understanding the language modeling challenge
- Core Architectures Behind LLMs
- Fully Connected Neural Networks and their role in ML
- RNNs and their limitations in handling long sequences
- Transformer architecture and its advantages
- Key components: Tokenization, Embeddings, and Encoder-Decoder models
- Understanding Key Concepts in Transformers
- Self-Attention mechanism and QKV matrices
- Tokenization and embedding demo in Python
- Pretraining vs Finetuning explained simply
- Inference tuning parameters: top-k, top-p, temperature
- Hands-On Labs and Demos
- Lab 1: Build a chatbot using Hugging Face
- Lab 2: Perform sentiment analysis on text data
- Lab 3: Create a simple translation model
- Live Python demos on tokenization, embeddings, and inferencing
- Evaluation and Inference Techniques
- BLEU and ROUGE scores for evaluating model outputs
- In-context learning: zero-shot, one-shot, and few-shot examples
Who This Course Is For:
- Beginners in AI/ML looking for a practical introduction to LLMs
- Developers curious about how models like ChatGPT work
- Students seeking a project-based approach to NLP and Generative AI
- Anyone interested in building their own language-based applications using open-source tools
This course combines intuitive explanations, real-world demos, and hands-on labs to ensure you walk away with both confidence and competence in working with LLMs and Generative AI.