Pre-Trained on SQuAD Dataset.
Used google BERT to build this Question_Answering System.
- python3
- pip3 install -r requirements.txt
model : bert-large-uncased-whole-word-masking
{"exact_match": 86.91579943235573, "f1": 93.1532499015869}Pretrained model download from here
unzip and move files to model directory