# Extractive Question Answering

Catalan question answering model based on RoBERTa architecture, excelling in Catalan Q&A tasks

This is an English extractive question answering model based on the ELECTRA-base architecture, trained on the SQuAD 2.0 dataset, suitable for question answering tasks.

A Thai extractive question answering model based on multilingual BERT, case-sensitive, suitable for Thai Q&A tasks.

DistilBERT is a lightweight distilled version of BERT, with 40% fewer parameters and 60% faster speed, maintaining over 95% of BERT's performance on the GLUE benchmark. This model is fine-tuned specifically for question answering tasks.