模型官方一手

StepFun 开源 Step 5 Preview:600B 参数 MoE,100 万上下文

StepFun Releases Step 5 Preview Open Weights: 600B MoE, 27B Active, 1M Context

精选理由

StepFun 把 Step 5 Preview 的权重直接开源了,600B 的 MoE 模型每次只激活 27B,还能塞 100 万 token 上下文,Hugging Face 上就能下载。

StepFun 发布 Step 5 Preview 开放权重模型,检查点已上线 Hugging Face 和 ModelScope,提供 FP8 和 BF16 两种格式。该模型采用稀疏 Mixture-of-Experts 架构,总参数 600B,每个 token 激活 27B。上下文窗口最高支持 1M tokens,面向长程智能体任务设计。

图片来源 · marktechpost
原文 · marktechpost

StepFun Releases Step 5 Preview Open Weights: 600B MoE, 27B Active, 1M Context

StepFun has released Step 5 Preview as open weights. FP8 and BF16 checkpoints are live on Hugging Face and ModelScope. Step 5 Preview is a sparse Mixture-of-Experts model from StepFun built for long-horizon agentic work. It has 600B total parameters, 27B active per token and up to 1M tokens of context. For developers, this is […] The post StepFun Releases Step 5 Preview Open Weights: 600B MoE, 27B Active, 1M Context appeared first on MarkTechPost .

  • 阶跃星辰 Stepfun10-15 13:00原文
  • NVIDIA AI10-15 13:52原文