← 返回快讯

快讯

Liquid AI 开源 d1 系列两个多模态模型:3B 支持文本+视觉,600M 支持文本+图像/音频

liquidai

Liquid AI 宣布发布 Open d1,开放权重的 d1 决策模型家族中新增两个多模态模型:d1-3B 支持文本+视觉,d1-omni-600M 支持文本+图像或文本+音频。公司称这些模型支持实时决策,可在从 NVIDIA DGX 数据中心到 RTX 工作站再到边缘端 Jetson 的多种设备上运行。

所属事件 →

事件来源

查看原文
RT Justin Li 李泽天 More d1s are here! 3B: Text + Vision 600M: Text+ Vision/Audio Now you can download run on your devices, let the D1s be with you 😋 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.

前后事件