Fine Tuning - Index - Sharon Zhou

 Module 1 -  Post-Training Overview

1. Conversation between Sharon Zhou and Andrew Ng

2. Background

3. LLM Training Stages

4. Intuitions behind fine-tuning and RL

5. Post Training Example - Reasoning

6. Post Training Example - Safety and Security

7. Post Training in the wild

8. Quiz

9. Lab  

 Module 2 - Core techniques in Fine-Tuning and RL

1. What you need to do and how to prepare it

2. Fine-tuning math - loss gradients and updates (part 1)

3. Fine-tuning math - loss gradients and updates (part 2)

4. Fine-tuning - Hyperparameters and hyperparameter tuning

5. Graded Lab

6. Fine-tuning - PEFT

7. RL - Rewards and Preference Learning 

          8. RL - Training Objective and RHLF 

          9. RL- PPO an d GRPO Algos

8. Quiz

9. Lab