@ModelScope2022
π₯ Meet dots.ocr-1.5: 3B OCR model from Rednote-hilab , SOTA multilingual document parsing, virtually any writing system. π Elo 1089 on olmOCR-Bench, 1157 on XDocParse β above GLM-OCR, and PaddleOCR-VL-1.5 π OmniDocBench text edit 0.031, beats Qwen3-VL-235B (0.069) and Gemini 2.5 Pro (0.075) π¨ SVG code output for charts, diagrams, and chemical formulas π Web parsing, scene text spotting, and object counting included β‘ vLLM supported, single GPU π€ Model: https://t.co/aTqXUALT5u π GitHub: https://t.co/nYtek81lm4 π Demo: https://t.co/q5RBPWpdpS