mrm8488/electra-small-finetuned-squadv1

Electra-small-discriminator fine-tuned on SQUAD v1.1 dataset for Q&A downstream task . Electra is a new method for self-supervised language representation learning . At large scale, ELECTRA achieves state-of-the-art results on the SQuAD 2.0 dataset . The model was trained on a Tesla P100 GPU and 25GB of RAM with the following command:python transformers/examples/question-answering/run_squad.py . The test set results were generated by Manuel Romero@m.m.488 | LinkedIn ♥ in Spain . The data set was created with the help of Manuel,