Fine-Tuning & PEFT
Updating weights, LoRA matrix arithmetic, SFT vs RFT, GRPO, and ART.
Fine-Tuning: LoRA & PEFT Math
advanced~12hLearn parameter-efficient fine-tuning, LoRA matrix arithmetic, rank selection, and SFT dataset generation.
GRPO: Group Relative Policy Optimization
advanced~12hMaster DeepSeek's reinforcement learning algorithm, group relative advantages, and training loops.
Dataset Engineering for LLMs
advanced~6hThe end-to-end discipline of building training data for LLMs: understanding what makes data high-quality, how to acquire and annotate it, how to augment it when real examples are scarce, and how to process raw data into clean, deduped, formatted training sets.
8 LoRA Fine-Tuning Variants Compared
advanced~4hLoRA, LoRA-FA, VeRA, Delta-LoRA, LoRA+, plus bonus techniques LoRA-drop, QLoRA, and DoRA — 8 distinct ways to parameter-efficiently fine-tune LLMs, compared.
SFT vs RFT: Choosing a Fine-Tuning Objective
intermediate~3hThe decision framework for choosing between supervised fine-tuning (static labeled data) and reinforcement fine-tuning (online reward-based exploration via GRPO) — including the full labeled-data/verifiability decision tree.
RL Environments for Agentic Fine-Tuning: OpenEnv & ART
advanced~4hThe environment-standardization problem in reinforcement learning, PyTorch's OpenEnv framework (containerized, Gymnasium-inspired), and OpenPipe's ART (Agent Reinforcement Trainer) for training agentic LLMs from experience.