{"id":"14252e5e-3e37-410c-bdd9-1c3ba7c31f4c","slug":"hf-model-damo-nlp-sg-videollama2-1-7b-av-v","name":"VideoLLaMA2.1-7B-AV","description":"Hugging Face model DAMO-NLP-SG/VideoLLaMA2.1-7B-AV. Task: visual question answering. Library: transformers. 2,292 downloads. 16 likes.","capabilities":["transformers","safetensors","videollama2_qwen2","text-generation","Audio-visual Question Answering","Audio Question Answering","multimodal large language model","visual-question-answering","en","dataset:lmms-lab/ClothoAQA","dataset:Loie/VGGSound","arxiv:2406.07476","arxiv:2306.02858","license:apache-2.0","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":45,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:36:11.140Z"}