# No-Answer Detection

QAmembert is a fine-tuned model based on CamemBERT for French question-answering tasks, trained on four French Q&A datasets, supporting both answer-present and no-answer scenarios.

A Polish QA system fine-tuned on a multilingual BERT model, trained on a machine-translated Polish SQuAD2.0 dataset

This model was established as a benchmark for the CS224n student project, based on the DistilBERT architecture and fine-tuned on the SQuAD2.0 dataset for question-answering tasks.

A lightweight question-answering model based on DistilBERT, fine-tuned on the SQuAD 2.0 dataset, supporting answering questions and detecting no-answer scenarios

A question-answering model fine-tuned on the SQuAD v2 dataset based on BERT base uncased version

This model is a QA system based on the Longformer architecture, fine-tuned on the SQuAD v2 dataset, supporting long text sequences (up to 4096 tokens).