VectorMindAll Topics
TechniquesAdvanced12 hrs

Fine-tuning & Alignment

Go beyond prompting. Learn LoRA, QLoRA, and full fine-tuning to adapt models to specific domains. Understand RLHF and DPO for behavior alignment.

Key Concepts

01LoRA
02QLoRA
03RLHF
04DPO
05Instruction Tuning
06PEFT
Study Note

This module covers teaching models to follow instructions. Work through the concepts in order — each one builds on the last. Return to this page as a reference after completing any related papers or implementations.

Module Info
LevelAdvanced
Duration12 hrs
CategoryTechniques
Concepts6 topics
Related Topics
Transformer ArchitectureLarge Language ModelsPrompt EngineeringRetrieval-Augmented Generation