LFM3 系列开放权重，涵盖文本、视觉和语音模型Chinese only
LFM3 系列的六款模型已在 Hugging Face 提供开放权重，覆盖文本、视觉、音频、多模态和决策任务，可针对数据在单张 GPU 上微调。发布方称，文本模型 LFM3-1.7B 比前代 LFM2.5-2.6B 少用 35% 参数，表现仍更好；首次推出的 LFM3-Omni-2B 可接收文字、图像、视频和音频，并输出文字或语音。
1 developments2 reports2 sources
Event developments 1
LFM3 models released with open weights for text, vision and audio
The six LFM3 models are available with open weights on Hugging Face. They cover text, vision, audio, multimodal and decision tasks, and each can be fine-tuned on a single GPU. The developer says LFM3-1.7B outperforms its predecessor, LFM2.5-2.6B, with 35% fewer parameters. Its first omni model, LFM3-Omni-2B, accepts text, images, video and audio and produces text or speech.
View source reports · 2 sources · 2 reports
All reports 2
Liquid AI releases LFM3 model family spanning text, vision and audio
The first six models are based on LFM3-1.7B-Base and span text, vision, decision-making, audio and multimodal tasks. Liquid AI says its LFM-1.7B text model has a 256K context window and outperforms the previous LFM2.5-2.6B while using 35% fewer parameters.
1 more source reported this
- Hugging Face 官方博客
LFM3 models released with open weights for text, vision and audio
The six LFM3 models are available with open weights on Hugging Face. They cover text, vision, audio, multimodal and decision tasks, and each can be fine-tuned on a single GPU. The developer says LFM3-1.7B outperforms its predecessor, LFM2.5-2.6B, with 35% fewer parameters. Its first omni model, LFM3-Omni-2B, accepts text, images, video and audio and produces text or speech.
1 more source reported this
- IT之家 科技新闻