Adaptation Strategies

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.

jpoindexter Updated 2 repo stars

File contents

jpoindexter/design-and-ai-skills commit c885fb78ff

Frequently asked questions

npx get-skill add jpoindexter/adaptation-strategies