{"id":"d5682038-01e1-44d7-8ca7-76d63dc87ade","slug":"hf-model-nkkbr-vica-thinking-1ifo9je-j","name":"ViCA-thinking","description":"Hugging Face model nkkbr/ViCA-thinking. Task: video text to text. Library: transformers. 19 downloads.","capabilities":["transformers","safetensors","llava","text-generation","multimodal","vision-language","video understanding","spatial reasoning","visuospatial cognition","qwen","llava-video","video-text-to-text","en","dataset:nkkbr/ViCA-322K","dataset:nkkbr/ViCA-thinking-2.68k","base_model:lmms-lab/LLaVA-Video-7B-Qwen2","base_model:finetune:lmms-lab/LLaVA-Video-7B-Qwen2","license:apache-2.0","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:40:03.486Z"}