{"id":"4b79a6fb-714f-43c5-9f3c-3154d8542490","slug":"hf-model-nkkbr-vica2-stage1-align-15wjzod-o","name":"ViCA2-stage1-align","description":"Hugging Face model nkkbr/ViCA2-stage1-align. Task: video text to text. Library: transformers. 23 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","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:20.773Z"}