Now, after almost two centuries, the mystery of what sparked this odd phenomenon is finally solved.ĭr. These four-horned, silver-white unicorns were previously unknown to science. Model Completion (machine-written, 10 tries) The scientist named the population, after their distinctive horn, Ovid’s Unicorn. While scores on these downstream tasks are far from state-of-the-art, they suggest that the tasks can benefit from unsupervised techniques, given sufficient (unlabeled) data and compute. On language tasks like question answering, reading comprehension, summarization, and translation, GPT-2 begins to learn these tasks from the raw text, using no task-specific training data.
In addition, GPT-2 outperforms other language models trained on specific domains (like Wikipedia, news, or books) without needing to use these domain-specific training datasets. GPT-2 displays a broad set of capabilities, including the ability to generate conditional synthetic text samples of unprecedented quality, where we prime the model with an input and have it generate a lengthy continuation. GPT-2 is a direct scale-up of GPT, with more than 10X the parameters and trained on more than 10X the amount of data. The diversity of the dataset causes this simple goal to contain naturally occurring demonstrations of many tasks across diverse domains.
GPT-2 is trained with a simple objective: predict the next word, given all of the previous words within some text. GPT-2 is a large transformer-based language model with 1.5 billion parameters, trained on a dataset of 8 million web pages. As an experiment in responsible disclosure, we are instead releasing a much smaller model for researchers to experiment with, as well as a technical paper. Due to our concerns about malicious applications of the technology, we are not releasing the trained model. Our model, called GPT-2 (a successor to GPT), was trained simply to predict the next word in 40GB of Internet text.
0 kommentar(er)
