AI NEWS.ccclef-omni
Clef-Omni is a 30B-A3B mixture-of-experts multimodal model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, audio, or video, and returns a probability for every allowed option of every question in a single forward pass. There is no free-form text generation and no output parsing. Clef-Omni is post-trained from Qwen/Qwen3-Omni-30B-A3B-Instruct. See Clef and Clef-Flash for the dense image and video variants. Tested with `torch` 2.11 and `transformers` 5.10.2 on a single H200; the backbone needs about 64 GB of GPU memory in bfloat16. Image inputs also need `pillow`, and audio and video files need `av`.
译文尚未就绪，显示来源原文
Clef-Omni is a 30B-A3B mixture-of-experts multimodal model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, audio, or video, and returns a probability for every allowed option of every question in a single forward pass. There is no free-form text generation and no output parsing. Clef-Omni is post-trained from Qwen/Qwen3-Omni-30B-A3B-Instruct. See Clef and Clef-Flash for the dense image and video variants. Tested with `torch` 2.11 and `transformers` 5.10.2 on a single H200; the backbone needs about 64 GB of GPU memory in bfloat16. Image inputs also need `pillow`, and audio and video files need `av`.