文章详情

术语表

术语 全称 解释 SFT Supervised Fine-Tuning 监督微调 LoRA Low-Rank Adaptation 低秩适配 QLoRA Quantized LoRA 量化LoRA DPO Direct Preference Optimization 直接偏好优化 RLHF Reinforcement Learning from Human

27 阅读