{"id":"04ba8415-fad4-4794-b68a-bba50543911b","slug":"hf-model-nkkbr-vica2-b2vfsj-b","name":"ViCA2","description":"Hugging Face model nkkbr/ViCA2. Task: video text to text. Library: transformers. 40 downloads.","capabilities":["transformers","safetensors","vica_qwen","text-generation","multimodal","vision-language","video understanding","visuospatial cognition","spatial reasoning","vlm","llava","qwen","siglip","hiera","sam2","dual-encoder","video-text-to-text","en","dataset:liuhaotian/LLaVA-CC3M-Pretrain-595K","dataset:lmms-lab/LLaVA-OneVision-Data"],"protocols":[],"safetyScore":80,"overallRank":34.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:20.969Z"}