Specializing Foundation Models with Fine-Tuning

О курсе

Specializing Foundation Models with Fine-Tuning equips you with the practical skills needed to adapt powerful pre-trained language models for domain-specific, high-impact applications. By completing this course, you will learn how to fine-tune large language models for custom NLP tasks, curate high-quality datasets from unstructured data, and rigorously evaluate both the performance and safety of generative AI systems using custom evaluation frameworks. The course takes a hands-on, end-to-end approach. You’ll begin by exploring advanced fine-tuning techniques such as Reinforcement Learning from Human Feedback (RLHF), Proximal Policy Optimization (PPO), and Direct Preference Optimization (DPO), gaining experience aligning model behavior with human preferences. You’ll then focus on transforming raw, unstructured data into curated datasets that meaningfully improve fine-tuned model performance. Finally, you’ll learn how to assess generative AI systems in real-world, high-stakes contexts, with an emphasis on governance, compliance, and responsible deployment. What makes this course unique is its multi-perspective design. It benefits from the expertise of IBM, Simplilearn, and Coursera, giving you exposure to diverse tools, workflows, and evaluation practices that reflect how fine-tuning and model assessment are performed across modern AI teams.

Навыки, которые вы освоите

Учитесь у экспертов

Professionals from the Industry

Преподаватель курса