deepset/xlm-roberta-base-squad2

For doing QA at scale (i.e. many docs instead of single paragraph) you can load the model also in haystack: FARMReader(model_name_or_path="deepset/xlm-roberta-base-squad2") You can load model & tokenizer in haystacks . For example in FARMInfrastructure: 4x Tesla v100 v100 . The model was evaluated on the SQuAD 2.0 dev set with the official eval script . It was also evaluated on German MLQA: test-context-de-question-de.de. It has been tested on German XQuAD: xquad,