Master advanced fine-tuning concepts with expert-level content and cutting-edge techniques.
Advanced linear algebra, optimization theory, probability theory
Expert in PyTorch/TensorFlow; experience with custom implementations
Transformers, explained: Understand the model behind GPT, BERT, and T5
AdvancedState-of-the-Art Machine Learning Papers Implementation
AdvancedNatural Language Processing Specialization
AdvancedLLM Fine-Tuning and Customization Training
AdvancedHarnessing LLMs: Strategy, Fine-Tuning & Evaluation Specialization
IntermediateFine-tuning and Reinforcement Learning for LLMs: Intro to Post-Training
IntermediateTransformers, explained: Understand the model behind GPT, BERT, and T5
AdvancedState-of-the-Art Machine Learning Papers Implementation
AdvancedNatural Language Processing Specialization
AdvancedLLM Fine-Tuning and Customization Training
AdvancedHarnessing LLMs: Strategy, Fine-Tuning & Evaluation Specialization
IntermediateFine-tuning and Reinforcement Learning for LLMs: Intro to Post-Training
IntermediateFollow these courses in order to complete the learning path. Click on any course to enroll.
Learn Transformers, explained: Understand the model behind GPT, BERT, and T5
State-of-the-Art Machine Learning Papers Implementation
Complete natural language processing specialization covering transformers, attention mechanisms, and modern NLP techniques.
This course on Coursera provides skills to optimize and deploy domain-specific large language models for advanced Generative AI applications. It covers supervised fine-tuning, parameter-efficient methods (PEFT), and reinforcement learning with human feedback (RLHF).
A comprehensive 7-course series that takes you from LLM business strategy to production deployment. You will learn to evaluate LLM opportunities, fine-tune models, and build production-ready applications using tools like Hugging Face and Python.
In partnership with AMD, this course teaches how to apply fine-tuning and reinforcement learning to improve LLM behavior, reasoning, and safety. You will learn about the post-training lifecycle, core techniques like RLHF and LoRA, and how to design evaluations to detect issues like reward hacking and diagnose failures.
Explore related content to expand your skills beyond this learning path.
Enroll in this path to track your progress and stay motivated.