Training & Fine-Tuning Models — From Foundations to LLMs

A hands-on, balanced course on how models are actually trained and adapted — from training fundamentals that apply to any model, through deep learning and large-scale transformer training, to fine-tuning LLMs with LoRA/QLoRA, SFT and DPO, and building small models. Concept + representative code, diagrams, quizzes, interview prep, and a final assessment.