Sebastian Raschka @rasbt

Big overhaul on DeepSeek V4.1 using an encoder-decoder setup. Tbh they should have called it DeepSeek V5! Super cool and refreshing, though! https://t.co/r00s3Cl29m [引用 @deepseek_ai]: 🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest model in our new architecture family, with native visual understanding. 🔹 Designed for greater capability, faster inference, higher throughput, and scaling to larger models. 1/6

• Raschka Traces Evolution of Text Classification Models2026-09-30
• OpenArch — PyTorch implementations of modern LLM architectures2026-09-14