google/electra-large-discriminator

Electra is a new method for self-supervised language representation learning . It can be used to pre-train transformer networks using relatively little compute . ELECTRA models are trained to distinguish "real" input tokens vs "fake" input . tokens generated by another neural network . At small scale, ELECTRA achieves strong results even when trained on a single GPU . It also supports fine-tuning ELECTRA on downstream tasks including classification tasks including QA tasks (e.g., SQuAD), and sequence tagging tasks . For a detailed description and experimental results, please refer to our paper ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators . For more,