NASA and IBM have jointly developed and released Surya, an open-source AI model designed to forecast solar weather, including solar flares and geomagnetic storms. Surya is trained on nine years of high-resolution imagery data from NASA's Solar Dynamics Observatory, totaling approximately 218 terabytes. The AI model employs a 366 million parameter transformer architecture and can predict solar activity up to two hours in advance, improving solar flare classification accuracy by 16% compared to previous methods. Surya aims to provide earlier warnings for potentially disruptive solar storms, such as Carrington-class events, which can impact critical technology and infrastructure on Earth. The model is available on the Hugging Face platform, enabling researchers worldwide to access and utilize it. This collaboration marks a significant advancement in heliophysics forecasting, with potential benefits for agencies like NASA and NOAA in predicting space weather phenomena, including auroras.