mrm8488/distilbert-multi-finetuned-for-xqua-on-tydiqa

DistilBERT multilingual fine-tuned on TydiQA (GoldP task) dataset for multilingual Q&A . This repository provides evaluation code and a baseline system for the dataset . It contains 200k human-annotated question-answer pairs in 11 Typologically Diverse languages . Unanswerable questions have been discarded, similar to MLQA and XQuAD . Thai and Japanese are removed since the lack of whitespace breaks some tools . The script is the following:.python transformers/examples/question-answering/run_squad.py . The model was fine tuned on a Tesla P100 GPU and 25GB of RAM .,