mrm8488/spanbert-base-finetuned-squadv1

Facebook Research fine-tuned SpanBERT on SQuAD 1.1 for Q&A downstream task (by them) Fine-tuning script can be downloaded from python code/run_squad . The numbers marked as * are evaluated on the development sets because those models were not submitted to the official SQAD leaderboard . All the other numbers are test numbers. All the numbers marked . are evaluated . on the . development sets . Because those models weren't submitted to . the official leaderboard, they are not . evaluated . The model was created by Manuel Romero/@mrm8488 and is based in Spain with the help of Facebook Research . It is now available,