mrm8488/electricidad-base-generator

ELECTRICIDAD: The Spanish Electra Imgur

Electricidad-base-generator (uncased) is a base Electra like model (generator in this case) trained on a + 20 GB of the OSCAR Spanish corpus.

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.

Fast example of usage 🚀

from transformers import pipeline

fill_mask = pipeline(
    "fill-mask",
    model="mrm8488/electricidad-base-generator",
    tokenizer="mrm8488/electricidad-base-generator"
)

print(
    fill_mask(f"HuggingFace está creando {fill_mask.tokenizer.mask_token} que la comunidad usa para resolver tareas de NLP.")
)

# Output: [{'sequence': '[CLS] huggingface esta creando herramientas que la comunidad usa para resolver tareas de nlp. [SEP]', 'score': 0.0896105170249939, 'token': 8760, 'token_str': 'herramientas'}, ...]

Acknowledgments

I thank 🤗/transformers team for allowing me to train the model (specially to Julien Chaumond).

Created by Manuel Romero/@mrm8488

Made with ♥ in Spain