{"id":"5254002d-11d2-4719-848b-f66ff4f2dee6","slug":"hf-model-audiovisual-caption-asid-captioner-7b-xehn4w-11","name":"ASID-Captioner-7B","description":"Hugging Face model AudioVisual-Caption/ASID-Captioner-7B. Task: image text to text. Library: transformers. 81 downloads. 8 likes.","capabilities":["transformers","safetensors","qwen2_5_omni","video-captioning","audiovisual","qwen2.5-omni","instruction-tuning","attribute-structured","quality-verified","image-text-to-text","conversational","en","arxiv:2602.13013","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":36.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:43.971Z"}