{"id":"e0bfa4f2-6e81-4a1c-9579-a0660952090f","slug":"hf-model-damo-nlp-sg-videollama3-7b","name":"VideoLLaMA3-7B","description":"Hugging Face model DAMO-NLP-SG/VideoLLaMA3-7B. Task: video text to text. Library: transformers. 3,612 downloads. 78 likes.","capabilities":["transformers","safetensors","videollama3_qwen2","text-generation","multi-modal","large-language-model","video-language-model","video-text-to-text","custom_code","en","dataset:lmms-lab/LLaVA-OneVision-Data","dataset:allenai/pixmo-docs","dataset:HuggingFaceM4/Docmatix","dataset:lmms-lab/LLaVA-Video-178K","dataset:ShareGPT4Video/ShareGPT4Video","arxiv:2501.13106","arxiv:2406.07476","arxiv:2306.02858","base_model:DAMO-NLP-SG/VideoLLaMA3-7B-Image","base_model:finetune:DAMO-NLP-SG/VideoLLaMA3-7B-Image"],"protocols":[],"safetyScore":80,"overallRank":46.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:36:04.805Z"}