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 Implementation and more info can be found in [this Github repository](https://github.com/prajjwal1/generalize_lm_nli).

Roberta-large trained on MNLI. 

----------------------
| Task    | Accuracy |
|---------|----------|
| MNLI    |   90.15  |
| MNLI-mm |   90.02  |

You can also check out:
- `prajjwal1/roberta-base-mnli`
- `prajjwal1/roberta-large-mnli`
- `prajjwal1/albert-base-v2-mnli`
- `prajjwal1/albert-base-v1-mnli`
- `prajjwal1/albert-large-v2-mnli`

[@prajjwal_1](https://twitter.com/prajjwal_1)