{"id":"7d436baf-6c95-40c1-af74-90d776631d90","slug":"hf-model-damo-nlp-sg-videollama3-2b-image-9tauzr-w","name":"VideoLLaMA3-2B-Image","description":"Hugging Face model DAMO-NLP-SG/VideoLLaMA3-2B-Image. Task: visual question answering. Library: transformers. 72 downloads. 8 likes.","capabilities":["transformers","safetensors","videollama3_qwen2","text-generation","multi-modal","large-language-model","video-language-model","visual-question-answering","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:Qwen/Qwen2.5-1.5B-Instruct","base_model:finetune:Qwen/Qwen2.5-1.5B-Instruct"],"protocols":[],"safetyScore":80,"overallRank":36,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:48.501Z"}