Fine-tuning & adaptation
5 questions
- The PM says: fine-tune the model on our docs so it knows our product. How do you respond?junior
- Full fine-tuning or LoRA? Walk me through how you decide, including the memory numbers.mid
- Explain LoRA mathematically. What do r and alpha control, and which modules would you target?mid
- DPO versus PPO-based RLHF: when would you choose each, and what does DPO give up?senior
- After a DPO run, reviewers say answers got longer and more flattering but not more accurate. What happened, and what do you do?senior