返回全部动态
腾讯发布Hy4 Preview：770B参数开源模型，推理强度可调
原标题：Introducing Hy4 Preview
AI 摘要
腾讯今日发布开源权重文本输入模型Hy4 Preview，总参数量770B，激活参数49B，上下文窗口1M token，Hugging Face上体积1.56TB，相比7月的Hy3大幅提升。模型支持两种推理强度：默认'high'和'no_think'（禁用推理）。作者通过SVG生成测试展示了其推理轨迹，并指出推理文本使用截断英文以节省token。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
29th August 2026 - Link Blog Introducing Hy4 Preview. New open weight text input (no vision) LLM from Chinese company Tencent today: 770B total parameters, 49B active parameters, 1M token context window, 1.56TB on Hugging Face. This is a big size increase from their previous Hy3 in July, which was 295B, 21B active, 256,000 context, 598GB. I recently started using model chat templates to better understand their capabilities. Here's Hy4's chat_template.jinja on Hugging Face, which includes this se
发布时间：2026-08-30 07:53
抓取时间：2026-08-30 08:20
来源机构：Simon Willison