{"id":"4d81c9e1-bb4f-4054-a524-2dd18a9ab32e","slug":"hf-model-kyutai-casa-qwen2-5-vl-3b-92x75g-p","name":"CASA-Qwen2_5-VL-3B","description":"Hugging Face model kyutai/CASA-Qwen2_5-VL-3B. Task: image text to text. Library: transformers. 185 downloads. 3 likes.","capabilities":["transformers","safetensors","qwen2_5vl_ca","feature-extraction","image-text-to-text","conversational","custom_code","en","dataset:HuggingFaceM4/FineVision","dataset:mvp-lab/LLaVA-OneVision-1.5-Instruct-Data","arxiv:2512.19535","base_model:Qwen/Qwen2.5-VL-3B-Instruct","base_model:finetune:Qwen/Qwen2.5-VL-3B-Instruct","license:cc-by-nc-sa-4.0"],"protocols":[],"safetyScore":80,"overallRank":38.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:12.100Z"}