mrm8488/mobilebert-uncased-finetuned-squadv2

MobileBERT is a thin version of BERT_LARGE, equipped with bottleneck structures and a carefully designed balance between self-attentions and feed-forward networks . 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 model was trained with the model training with the . following command . It converges much faster than other ones, so it is also cheap to fine-tune and converges faster than . other ones . Model training was trained using the Tesla . P100 P100 with the Model trained on 25GB RAM with,