Generative AI Fundamentals with Hugging Face

Ready to build applications with powerful language models but not sure where to start? This course provides a clear, text-based path into the world of generative AI using the essential tools from the Hugging Face ecosystem. By the end of this course, you will understand the complete workflow for working with Large Language Models (LLMs). You'll move from core concepts like Transformers and tokenization to the practical skills needed to customize pre-trained models for specific tasks, such as text summarization and creative content generation. What you'll learn: - Understand the core concepts behind Transformers and Large Language Models. - Navigate the Hugging Face Hub to find and use pre-trained models and datasets. - Master the tokenization process to prepare your text data for model input. - Practice fine-tuning an existing LLM on a custom dataset to adapt it for a specific task. - Apply parameter-efficient fine-tuning (PEFT) techniques to train models with less compute. - Learn to optimize models for inference using methods like quantization. - Explore common LLM application patterns, including Retrieval-Augmented Generation (RAG). The course begins with foundational theory before progressing to hands-on exercises covering data preparation, model selection, fine-tuning, and optimization. You will read detailed explanations and practice with written examples to build your skills step-by-step. This course is designed for beginners. No prior experience with Hugging Face or deep learning is required, though a basic understanding of Python will be helpful. Start your journey into the world of generative AI today.