面壁智能开源交互模型 Gander,代码、模型、技术报告以及推理和训练配置均已放出。该模型使用约 2.7M 条交互样本训练,覆盖语音交互、音视频交互、智能体交互以及鲁棒性与负样本数据。训练不仅关注说什么,也关注何时倾听、何时回应、何时打断和何时委派。
🚀 Building natural interaction requires more than a larger model.
Gander was trained on ~2.7M interaction examples covering:
🎙️ Speech interaction
👀 Audio-visual interaction
🤖 Agentic interaction
🛡️ Robustness & negative data
The training focuses not only on what to say, but also when to listen, when to respond, when to interrupt, and when to delegate.
Gander is now open source, with the code, model, technical report, and inference/training setup available for developers and researchers to explore.
🔗 GitHub: https://t.co/FFDY8z9IVI
📄 Technical Report: https://t.co/i0Vabolok8
🤗 Model: https://t.co/R1EzUbsEAW
https://t.co/bRcld16Jco
来源:@OpenBMB · x.com