OPD_SNR Model_Parallel ZeRO Connections Between On Policy Distillation And RL Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation Instruction tuning with loss over instructions Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning RETAINING BY DOING: THE ROLE OF ON-POLICY DATA IN MITIGATING FORGETTING Proximal Gradient and Subgradients Importance-Aware Data Selection for Efficient LLM Instruction Tuning More...

Different Designs For LLM KD Loss(II) Training-Inference Mismatch In LLM KD(II) SVD Decompositon in LLM Compression Training-Inference Mismatch In LLM KD Different Designs For LLM KD Loss

SGD收敛性学习笔记 Reparameterization-Trick Attention-Machanism

环论 群作用 Burnside 引理

Dilworth 定理 多项式EXP运算的组合意义 树与图上计数问题：Prufer序列与LGV引理

hexo+reveal指南 服务器转发流量至本地 服务器炼丹手册

练琴有感 伍六七观后小感 杂想-抽奖问题平凡解

高维前缀和学习笔记 各类基于决策单调性的dp优化 斜率优化dp总结

从REINFORCE到PPO VAE学习笔记

编译原理实验七-sql简易编译器 编译原理实验六-对表达式的解析

Bug聚集地

二分图博弈学习笔记

势函数与鞅的停时定理