Essay · AI Blog · Ahead of AI · Sebastian Raschka

From DeepSeek V3 to V3.2: Architecture, Sparse Attention, and RL Updates

作者 Sebastian Raschka, PhD 2025-12-03 · 350 天前 English
From DeepSeek V3 to V3.2: Architecture, Sparse Attention, and RL Updates
Summary · 摘要

Understanding How DeepSeek's Flagship Open-Weight Models Evolved

阅读原文 magazine.sebastianraschka.com