Rethinking the Role of Temperature in Large Language Model Distillation 文章

ArXiv CS.AI2026-06-02NEWSen作者: Hoang-Chau Luong, Lingwei Chen
查看原文 →
关系图谱

Rethinking the Role of Temperature in Large Language Model Distillation · 相关技术

相关技术

distillationlarge language modelsforward KLKullback-Leibler divergence