view article Article LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family Jan 19 • 88
Runtime error Featured 162 DocOwl 📚 162 Interact with documents and images to get explanations and answers
Running Featured 238 PaddleOCR-VL Online Demo 📈 238 Extract text, tables, formulas, and charts from images
gpt-oss Collection Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7, 2025 • 420
Essential-Web v1.0: 24T tokens of organized web data Paper • 2506.14111 • Published Jun 17, 2025 • 46