NEW
Fine-Tuning LLMs: When to Use SFT, RLHF, or DPO and How Quantization Affects Memory
Before we get into it, the short version: Two tables below show memory, quality, and hardware trade-offs across fine-tuning methods. First table covers general characteristics. Summary blocks after it explain when you'd pick each approach. Memory summary: Full fine-tuning updates every weight, so…
