t5-large

Study compares pre-training objectives, architectures, unlabeled datasets, transfer approaches, and other factors on dozens of language understanding tasks . To facilitate future work on transfer learning for NLP, we release our dataset, pre-trained models, and code . We achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more . [Google's T5: C4; C4: Pretraining Dataset; C6: C6; C7: C7; C8: C9: C3: C5; C5: P6: P7: P8: P9: P3: P,