開發工作常要同時看懂圖片或影片、操作電腦,還要處理程式和研究任務。
- Tencent 開放了多模態模型 Hy4 的權重。
- 它有 770B 引數的語言模型骨幹,每個 token 啟用 49B,能處理文字、圖片和影片,並支援 1M-token 上下文。Hy4 也結合畫面理解與 CLI、GUI 工具操作,針對 Blender、CAD 和跨應用程式流程訓練,並為 Unreal Engine、Unity 和 Godot 的遊戲開發做了調整。原文稱它在 OSWorld 2.1、Tencent 內部研究基準 TenureTrail,以及 579 項金融任務評測中領先受測的開放權重模型。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
Hy4 把影片與圖片理解、電腦操作和多款遊戲引擎開發放在同一模型中,文中也列出它在三項測試中的表現。
Hy4 is now open-weight. Tencent’s multimodal flagship has a 770B language backbone with 49B active per token, a 1M-token context, and text, image, and video understanding for coding, computer use, and research.
🤖 https://t.co/F8iv7emnS9
🏆 Strong agent results. Leads the evaluated open-weight models on OSWorld 2.1, Tencent’s internal TenureTrail research benchmark, and its 579-task finance evaluation.
🖥️ Vision meets execution. Combines visual understanding with CLI and GUI tool use, with targeted training for Blender, CAD, and workflows spanning multiple applications.
🎮 Built for game development. Adapted for Unreal Engine, Unity, and Godot, covering gameplay logic, state tracking, asset pipelines, and multiplayer development.
🛠️ Deploy and customize. FP8 weights, vLLM/SGLang serving, and official ms-swift scripts for full and LoRA fine-tuning on text and vision-language tasks.