跳到正文
arXiv Artificial Intelligence· Yue He, Jiahui Hu, Shaman Tang, Hua Zhou, Qiman Wu, Menglin Li, Yizhao Wang, Yuheng Zhang, Da Zhu, Zhou Wang, Anhua Liu, Hanlin Chen, Mingyuan Wang, Rui Xin, Yuhua Wei, Shuang Su, Siqi Liu, Kai Yang, Weichao Huang, Hang Zhang, Honggou Yang, Xianming Liu·· 17 小时前AI 评分40

Turing LLM 后训练:校准蒸馏与高效动态 MoE 执行

Turing LLM Post-Training: Calibrated Distillation and Efficient Dynamic-MoE Execution

AI 导读

Turing-20B-A2B 通过校准多教师同策略蒸馏(C-MOPD)与动态 MoE 执行路径,在四领域归一化集成得分达 0.9988,每个领域至少保留 90.16% 的专家增益。

来源:arXiv Artificial Intelligence · arxiv.org