mrm8488/legalectra-small-spanish

LEGALECTRA ⚖️

LEGALECTRA (small) is an Electra like model (discriminator in this case) trained on A collection of corpora of Spanish legal domain.

As mentioned in the original paper: ELECTRA is a new method for self-supervised language representation learning. It can be used to pre-train transformer networks using relatively little compute. ELECTRA models are trained to distinguish "real" input tokens vs "fake" input tokens generated by another neural network, similar to the discriminator of a GAN. At small scale, ELECTRA achieves strong results even when trained on a single GPU. At large scale, ELECTRA achieves state-of-the-art results on the SQuAD 2.0 dataset.

For a detailed description and experimental results, please refer the paper ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators.

Training details

The model was trained using the Electra base code for 3 days on 1 Tesla V100 16GB.

Model details ⚙

Param	# Value
Layers	12
Hidden	256
Params	14M

Evaluation metrics (for discriminator) 🧾

Metric	# Score
Accuracy	0.955
Precision	0.790
AUC	0.971

Benchmarks 🔨

WIP 🚧

How to use the discriminator in transformers

TBA

Acknowledgments

TBA

Citation

If you want to cite this model you can use this:

@misc{mromero2022legalectra,
  title={Spanish Legal Electra (small)},
  author={Romero, Manuel},
  publisher={Hugging Face},
  journal={Hugging Face Hub},
  howpublished={\url{https://huggingface.co/mrm8488/legalectra-small-spanish},
  year={2022}
}

Created by Manuel Romero/@mrm8488

Made with ♥ in Spain