SemiAnalysis@SemiAnalysis_ · XAI 摘要
情况检测到：里约热内卢市后训练了一个模型。 基于 Qwen 7/2，Rio 3.5 Open 397B 在基础 Qwen 模型之上添加了 SwiReasoning——一个在标准链式推理与隐空间推理之间动态切换的框架，由基于熵的置信信号引导，使模型仅在必要时"出声思考"，其余时间在隐藏空间内静默推理，以提高 token 效率。
SITUATION DETECTED： The city of Rio de Janerio has post-trained a model.
Based on Qwen 7/2， Rio 3.5 Open 397B adds SwiReasoning on top of the base Qwen model - a framework that dynamically switches between standard chain-of-thought and latent-space reasoning， guided by entropy-based confidence signals， so the model only "thinks out loud" when it needs to and otherwise reasons silently in hidden space for better token efficiency.