{"id":"945c9e21-3ad9-414e-915a-484d15730c23","slug":"hf-model-nvidia-4d-rgpt-8b-1fouc22-h","name":"4D-RGPT-8B","description":"Hugging Face model nvidia/4D-RGPT-8B. Task: video text to text. Library: transformers. 173 downloads. 17 likes.","capabilities":["transformers","safetensors","llava_llama","multimodal","video-understanding","region-grounding","3d-reasoning","4d-reasoning","perceptual-distillation","nvila","vila","video-text-to-text","en","dataset:nvidia/R4D-Bench","arxiv:2512.17012","base_model:Efficient-Large-Model/NVILA-Lite-8B","base_model:finetune:Efficient-Large-Model/NVILA-Lite-8B","license:cc-by-nc-4.0","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":38.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:14.714Z"}