{"id":"140b7712-3efc-4547-b7a0-1bc2cece88a9","slug":"hf-model-nkkbr-vica2-init-b7nks4-g","name":"ViCA2-init","description":"Hugging Face model nkkbr/ViCA2-init. Task: video text to text. Library: transformers. 19 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","license:apache-2.0","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:40:03.486Z"}