Transformer quantum state: A multipurpose model for quantum many-body problems

Inspired by the advancements in large language models based on transformers, we introduce transformer quantum state (TQS): a versatile machine learning model for many-body problems. In sharp contrast to Hamiltonian/task specific models, TQS can generate entire phase diagram, predict field strengths with experimental measurements, and transfer such knowledge new systems it has never been trained before, all within single model. With tasks, fine-tuning produces accurate results small computational cost. Versatile design, be easily adapted thereby pointing towards general-purpose various challenging