{"id":"cbde2ade-675a-4968-a59d-af7a1879cd53","slug":"hf-model-docling-project-screenvlm-uq4th5-p","name":"ScreenVLM","description":"Hugging Face model docling-project/ScreenVLM. Task: image text to text. Library: transformers. 615 downloads. 7 likes.","capabilities":["transformers","safetensors","idefics3","image-text-to-text","text-generation","screen-parsing","ui-understanding","object-detection","grounding","web","screentag","docling","granite","conversational","en","dataset:docling-project/screenparse","arxiv:2602.14276","license:apache-2.0","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":41.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:36:30.988Z"}