Verified record · from the answer index

finetuning-method-selection

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 ch

skill:wshobson/agents/finetuning-method-selection · published by wshobson · source repository