快讯
Liquid AI 开源 d1 决策模型家族：d1-3B 视觉语言模型与 d1-omni-600M 多模态模型
Liquid AI 宣布开源 Open d1 系列两个开放权重多模态决策模型：d1-3B 支持文本+视觉，d1-omni-600M 支持文本+图像或文本+音频。官方称这些模型可用于实时决策，部署范围从 NVIDIA DGX 数据中心到 RTX 工作站再到 Jetson 边缘设备。相关表述均为作者/团队声称，未经独立核实。
查看原文
RT Aurélien Lac Most decisions don't need a big model. They need a fast one. Today we're open sourcing d1-3B, a vision-language decision model, and d1-omni-600M, which takes text, images and audio. Liquid AI: Today we release Open d1: two open-weight multimodal models in our d1 decision model family. > d1-3B: text + vision > d1-omni-600M: text + image or text + audio > Real-time decision making anywhere, from data centers such as @nvidia DGX to RTX workstations to Jetson at the edge.