Pretrained model using a masked language modeling (MLM) objective. Fine tuned on English and Russian QA datasets
SQuAD + SberQuAD
SberQuAD original paper is here! Recommend to read!
The results obtained are the following (SberQUaD):
f1 = 84.3 exact_match = 65.3
Select AutoNLP in the “Train” menu to fine-tune this model automatically.
- Downloads last month