Decide whether to fine-tune at all, and route to the right method (SFT, DPO/ORPO/KTO, GRPO/RLVR, continued pretraining) and base model. Use when starting any fine-tuning effort, when unsure whether RAG or prompting would suffice, or when choosing between preference-optimization and reinforcement methods.
安装
尚未确认此技能的独立目录。下面命令会打开仓库技能选择器，请按上游说明选择技能。
skills CLI
npx skills add wshobson/agents