Decision framework for making a model do a task — choosing between in-context learning, RAG, fine-tuning (LoRA/QLoRA/DPO), and distillation. Maps the gap you have (knowledge / behavior / capability / cost) to the right lever, names when each is the WRONG tool, and covers data requirements, eval, cat
Decision framework for making a model do a task — choosing between in-context learning, RAG, fine-tuning (LoRA/QLoRA/DPO), and distillation. Maps the gap you have (knowledge / behavior / capability / cost) to the right lever, names when each is the WRONG tool, and covers data requirements, eval, catastrophic forgetting, and combining methods.