d1-omni-600M is an experimental 600M-parameter model for text + image or text + audio. It combines LFM2.5-Encoder-350M with vision and audio encoders, and leads our text benchmark comparison in toxicity detection and paraphrase identification. Use it for voice-command routing, on-device moderation, and intent classification. 3/
d1-omni-600M is an experimental 600M-parameter model for text + image or text + audio.
AISummary
d1-omni-600M is an experimental 600M-parameter model for text + image or text + audio. It combines LFM2.5-Encoder-350M with vision and audio encoders, and leads our text benchmark comparison in toxicity detection and paraphrase identification. Use it for voice-command routing, on-device moderation, and intent classification. 3/
Source: Liquid AI · x.com