Liquid AI 发布开放权重的 LFM3 多模态模型家族
Liquid AI 发布了 LFM3 模型家族，首批六款模型规模约为 20 亿参数，覆盖文本、视觉、音频、全模态和决策任务，并采用统一的混合骨干。这些模型使用 22T 词元预训练，基础模型和后训练模型的开放权重可通过 Hugging Face、Liquid AI Playground 和 Liquid AI API 获取。Liquid AI 称，LFM3-1.7B 的参数量比 LFM2.5-2.6B 少 35%，4-bit 精度下约占 1GB，并支持 256K token 上下文窗口。
此次发布为开发者提供了覆盖多种模态和专用任务的开放权重模型。这些模型可进行微调，并在手机、笔记本及边缘设备等硬件上进行本地部署。
Today, we’re excited to announce LFM3, our new generation of Liquid Foundation Models (LFMs) built for specialized intelligence. The LFM3 model family is multimodal by nature and brings text, vision, audio, omni, and decision models onto one new shared backbone. The first release of the LFM3 family covers models in the 2B parameter range.
Built on a new hybrid architecture and 22T tokens of pre-training, LFM3 is far more expressive than LFM2 while maintaining its efficiency. The extra capacity in a small, fast model makes LFM3 the ideal starting point in its class for specialized intelligence: this is because it can be fine-tuned locally, it can run on any device, and it is capable enough to become a reliable expert on a specialized task.
The base and post-trained models are open-weight and available today on Hugging Face, our Playground, and the Liquid AI API. Check out our docs on how to run and fine-tune them locally.
#Liquid AI#LFM3#LFM3-1.7B#LFM3-1.7B-Base#LFM3-VL-2B#LFM3-Audio-2B#LFM3-Omni-2B#d1-2B#d1-Omni-2B#Hugging Face