preference-optimization

【数据与研究】Align a fine-tuned model with preference data using DPO, ORPO, KTO, or SimPO. Use when preference pairs or thumbs-up/down feedback exist, when choosing between preference-optimization methods, or when a DPO run needs hyperparameters or debugging.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准