Transformer 架构变化：旋转位置编码 (RoPE) 05-24

Transformer 架构变化：RMSNorm 指南 05-11

语言模型中的 Weight Tying 技术 03-11

GraphRAG 工作流 02-11

论文阅读: Outrageously Large Neural Networks-The Sparsely-Gated Mixture-of-Experts Layer 02-02

论文阅读: Generalization through Memorization: Nearest Neighbor Language Models 12-23

论文阅读: In-Context Retrieval-Augmented Language Models 12-04

论文阅读: REALM: Retrieval-Augmented Language Model Pre-Training 11-30

LoRA 微调 09-14

用 MPNN 框架解读 GAT 05-21