mrm8488/roberta-base-1B-1-finetuned-squadv1

RoBERTa-base (1B-1) + SQuAD v1.1 fine-tuned on 'SQ&A' dataset for Q&A downstream task . They combine English Wikipedia and a reproduction of BookCorpus using texts from smashwords in a ratio of approximately 3:1 . 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 . Model training was trained using the model on a . Tesla . P100 with 25GB RAM and a Tesla . model trained on . a Tesla. P100 . model with the .,