mrm8488/electricidad-base-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 . At large scale, electra achieves state-of-the-art results on the SQuAD 2.0 dataset . I thank Manuel Romero/@mrm8488 for allowing me to train the Electra model (specially to Julien Chaumond). The Spanish Electra Imgur Imgur model was created by Manuel,