PART VIII — Fine-Tuning & Alignment

 

Chapter 18: Fine-Tuning LLMs

Goal: Adapt base models

Topics Covered:

• Supervised fine-tuning

• Instruction tuning

• Domain adaptation

• Catastrophic forgetting

📌 Medium Post 18: Fine-Tuning Language Models Explained

---

Chapter 19: Alignment & RLHF

Goal: Make models helpful and safe

Topics Covered:

• Why alignment is needed

• Human feedback loops

• Reward models

• PPO overview

📌 Medium Post 19: How LLMs Are Aligned with Human Intent