Primer/bart-squad2

BART-Squad2 is a model for extractive (span-based) question answering, trained on Squad 2.0 . The Huggingface auto-inference API won't run this model, so if you're attempting to try it through the input box above and it complains, don't be discouraged! In a technical sense one big limitation is that it's 1.6G (1.1f) The model has a rating of 87.4, but it has a rate of 1.8f . The model is based on a model that was trained on the current version of the BART platform . It is now available to download and use for the next version of,