快讯
Liquid AI 发布 Open d1:两个开源多模态决策模型
团队表示,Liquid AI 今日发布 Open d1 系列,包含两个开源权重的多模态模型:d1-3B(文本+视觉)和 d1-omni-600M(文本+图像或文本+音频)。团队称这些模型支持实时决策,可从 NVIDIA DGX 数据中心部署到 RTX 工作站,再到 Jetson 边缘设备。
查看原文
RT Amit Naik 👀 Jev can see now - Open source! 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.