Bert Medium Mnli

🚀 BERT Pre - trained Model

This is a PyTorch pre - trained model converted from a TensorFlow checkpoint from the official Google BERT repository. It addresses natural language understanding tasks and provides high - performance results on MNLI.

🚀 Quick Start

The following model is a Pytorch pre - trained model obtained from converting Tensorflow checkpoint found in the 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.

📚 Documentation

Performance

MNLI: 75.86%
MNLI - mm: 77.03%

These models are trained for 4 epochs.

Citation

If you use the model, please consider citing the paper

@misc{bhargava2021generalization,
      title={Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics}, 
      author={Prajjwal Bhargava and Aleksandr Drozd and Anna Rogers},
      year={2021},
      eprint={2110.01518},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Original Source

Original Implementation and more info can be found in this Github repository.

Contact

@prajjwal_1