MiniMax M2 and Production-Oriented Model Design

Sebastian Raschka, PhD，Sebastian Raschka 的个人主页，AI 研究员与教育者，《Build a Large Language Model (From Scratch)》作者。关注

Short note on the MiniMax-M2 technical report, including full attention, fine-grained MoE, agent pipelines, speed rewards, and self-evolution.

添加评论
点赞收藏
点踩分享查看原文
评论
?
参与讨论