prajjwal1/bert-mini-mnli

Pytorch pre-trained model obtained from converting Tensorflow checkpoint found in official Google BERT repository . These BERT variants were introduced in the paper Well-Read Students Learn Better: On the Importance of Pre-training Compact Models . These models are trained on MNLI.MNLI: 68.04%.                MNLI-mm: 69.17%                 receive-pre-trained models were trained for 4 epochs.                 MNLI: phenomenal -referred-to-prepared-preformed models.                @prajjwal_1: referfer-prepre-training models were trained for four epoch,