Liquid AI 发布开源边缘决策模型 d1-3B 与 d1-omni-600M
原标题：Multimodal open d1 decision models for the edge
AI 摘要
Liquid AI 在 Hugging Face 发布两款开源决策模型 d1-3B 和 d1-omni-600M，基于其 Liquid Foundation Models 构建，不生成 token 而是单次前向传播给出答案。d1-3B 在 Decision Index 0.2.1 上以 48.57 分成为 10B 以下最佳决策模型，支持文本和图像，在 NVIDIA Jetson AGX Thor 上单次回答仅需 16ms。d1-omni-600M 支持文本加图像或文本加音频，目前为早期研究版本。两款模型均已开源并可在 Hugging Face 下载。
正文节选
- Best decision model under 10B on the Decision Index 0.2.1: d1-3B scores 48.57, ahead of every 4B and 9B model and of Decider 35B-A3B (47.11). - Multimodal: d1-3B supports text and images, while d1-omni-600M supports text and images or text and audio - Fast: d1-3B answers a question in 16 ms on an NVIDIA Jetson AGX Thor, 26 ms on a Jetson AGX Orin, and 50ms on a Jetson Orin Nano These open d1 decision models are built on our Liquid Foundation Models (LFMs). Unlike our generative models, decisio