{"id":"7b6823ae-eb2f-4a7e-993c-679ee302306c","slug":"hf-model-harryhsing-omniagent-sft-7b-1r86gtj-r","name":"OmniAgent-SFT-7B","description":"Hugging Face model harryhsing/OmniAgent-SFT-7B. Task: video text to text. Library: transformers. 28 downloads. 1 likes.","capabilities":["transformers","safetensors","qwen2_5_omni","text-to-audio","omni-modal","video-understanding","multimodal-llm","agent","active-perception","video-text-to-text","en","zh","arxiv:2606.19341","base_model:Qwen/Qwen2.5-Omni-7B","base_model:finetune:Qwen/Qwen2.5-Omni-7B","license:apache-2.0","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:52.032Z"}