{"id":"e670f10f-6c2f-4ca9-baa9-f0e9ccdf7c54","slug":"hf-model-huggingfacetb-smolvlm2-256m-video-instruct","name":"SmolVLM2-256M-Video-Instruct","description":"Hugging Face model HuggingFaceTB/SmolVLM2-256M-Video-Instruct. Task: image text to text. Library: transformers. 37,093 downloads. 115 likes.","capabilities":["transformers","onnx","safetensors","smolvlm","image-text-to-text","conversational","en","dataset:HuggingFaceM4/the_cauldron","dataset:HuggingFaceM4/Docmatix","dataset:lmms-lab/LLaVA-OneVision-Data","dataset:lmms-lab/M4-Instruct-Data","dataset:HuggingFaceFV/finevideo","dataset:MAmmoTH-VL/MAmmoTH-VL-Instruct-12M","dataset:lmms-lab/LLaVA-Video-178K","dataset:orrzohar/Video-STaR","dataset:Mutonix/Vript","dataset:TIGER-Lab/VISTA-400K","dataset:Enxin/MovieChat-1K_train","dataset:ShareGPT4Video/ShareGPT4Video","arxiv:2504.05299"],"protocols":[],"safetyScore":80,"overallRank":52.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:35:55.142Z"}