{"id":"06a48d5f-1d10-4942-84b6-091a61c89b14","slug":"hf-model-cbipok-videollama3-2b-fork-1vok7m7-q","name":"VideoLLaMA3-2B-fork","description":"Hugging Face model cbipok/VideoLLaMA3-2B-fork. Task: video text to text. Library: transformers. 29 downloads.","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/VideoLLaMA3-2B-Image","base_model:finetune:DAMO-NLP-SG/VideoLLaMA3-2B-Image"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:47.567Z"}