We've trained a large-scale unsupervised language model which generates coherent paragraphs of text, achieves state-of-the-art performance on many language modeling benchmarks, and performs rudimentary reading comprehension, machine translation, question answering, and summarization-all without task-specific training. View code Read paper Our model, called GPT-2 (a successor to GPT), was trained simply to predict the next word in 40GB of Internet text.