云声发布 U2-Flash MoE 模型,用于代理和编程任务
Unisound Launches U2-Flash MoE as Post-Training RSI Flagship Flash Model
云声发布了 U2-Flash MoE 模型,这个模型有 266B 参数,10B 活跃参数,专门用于代理和编程,比之前的版本更好。
云声推出 U2-Flash 模型,这是一个约 266B 的稀疏 MoE 模型,拥有约 10B 个活跃参数,采用后训练递归自我改进和潜在推理技术,专门用于代理和编程工作负载,现已在其 MaaS 平台上上线。
Unisound Launches U2-Flash MoE as Post-Training RSI Flagship Flash Model
Unisound unveiled U2-Flash, a ~266B sparse MoE with ~10B active parameters, pairing post-training recursive self-improvement and latent reasoning for agent and coding workloads, now live on its MaaS platform.