{"id":"e5141e82-e3c7-42dd-b176-9c3e8ba9a614","slug":"hf-model-damo-nlp-sg-videorefer-videollama3-7b-1l6sqtw-11","name":"VideoRefer-VideoLLaMA3-7B","description":"Hugging Face model DAMO-NLP-SG/VideoRefer-VideoLLaMA3-7B. Task: video text to text. Library: transformers. 60 downloads. 13 likes.","capabilities":["transformers","safetensors","videollama3_qwen2","text-generation","multimodal large language model","large video-language model","video-text-to-text","custom_code","en","arxiv:2406.07476","arxiv:2501.00599","arxiv:2504.16072","arxiv:2501.13106","base_model:DAMO-NLP-SG/VideoLLaMA3-7B-Image","base_model:finetune:DAMO-NLP-SG/VideoLLaMA3-7B-Image","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":35.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:57.261Z"}