MiniCPM4.1-8B: First Open-Source Reasoning LLM with Trainable Sparse Attention

🚀 Introducing MiniCPM4.1-8B: First Open-Source Reasoning LLM with Trainable Sparse Attention ✅ Strong Reasoning Capability: Surpasses similar-sized models on 15 tasks! ✅ Fast Generation: 3x decoding speedup for reasoning ✅ Efficient Architecture: Trainable sparse attention, frequency-ranked speculative decoding Download Models: Huggingface: https://huggingface.co/openbmb/MiniCPM4.1-8B Github: https://github.com/OpenBMB/MiniCPM Technical Report: https://arxiv.org/pdf/2506.07900