Fine-tuning decision tree for 2026: QLoRA SFT → DPO → GRPO when your reward is verifiable

Future AGI·medium signal

The 2026 verdict for reasoning/code fine-tuning: start with QLoRA SFT using unsloth on a single H100, layer DPO (or ORPO/KTO) if you have preference pairs, and switch to GRPO once your reward function is verifiable. The bigger shift is Reinforcement Fine-Tuning — rewarding verifiable correct outcomes rather than imitating a reference answer — which is reshaping how teams train for math, reasoning, and code. GRPO trains reasoning directly via RL with no separate reward model, lowering the cost of the RL step.