{"id":"fdcdd99e-8c79-4fc3-8c4b-6e57a74610e1","slug":"hf-model-damo-nlp-sg-videorefer-videollama3-2b-1l6sqpb-11","name":"VideoRefer-VideoLLaMA3-2B","description":"Hugging Face model DAMO-NLP-SG/VideoRefer-VideoLLaMA3-2B. Task: video text to text. Library: transformers. 56 downloads. 7 likes.","capabilities":["transformers","safetensors","videollama3_qwen2","text-generation","multimodal large language model","large video-language model","video-text-to-text","en","arxiv:2406.07476","arxiv:2501.00599","arxiv:2504.16072","arxiv:2501.13106","base_model:DAMO-NLP-SG/VideoLLaMA3-2B-Image","base_model:finetune:DAMO-NLP-SG/VideoLLaMA3-2B-Image","license:apache-2.0","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":35.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:03.106Z"}