Large Language Models with Hugging Face

Master the essential skills to build production-ready applications powered by large language models in this course. You'll learn to control text generation with precision using sampling parameters and stopping criteria, design effective prompts with chat templates for instruction-tuned models, build retrieval-augmented generation (RAG) pipelines that enable LLMs to access external knowledge, and extract structured data through constrained generation and function calling. What makes this course unique is its hands-on approach to practical LLM application development. You'll work directly with popular open-source models like Llama, Mistral, and Phi, progressing from basic text generation to sophisticated agent systems. Unlike theoretical courses, you'll build real systems—a semantic search engine with sentence-transformers, a complete RAG-powered question-answering pipeline, and tool-using agents that can execute functions based on LLM reasoning. Whether you're developing chatbots, automating information extraction, or building AI assistants, this course equips you with battle-tested patterns and techniques used in production LLM systems. You'll gain the confidence to choose the right approach for your use case and the skills to implement it reliably using the Hugging Face ecosystem.