mrm8488/spanbert-finetuned-squadv1

SpanBERT (spanbert-base-cased) fine-tuned on SQuAD v1.1 for Q&A downstream task . The model was trained on a Tesla P100 GPU and 25GB of RAM . The script for fine tuning can be found here: SpanBERT is a pre-training method that is designed to better represent and predict spans of text . It was created by Facebook Research and fine-tuneed for the downstream task (Q&A) - Dataset. 1.1 contains 100,000+ question-answer pairs on 500+ articles. The model has been trained on . a Tesla . P100 with 25GB RAM.,