keras/

electra_small_generator_uncased_en

ELECTRA model is a pretraining approach for language models published by Google. Two transformer models are trained, a generator and a discriminator. The generator replaces tokens in a sequence and is trained as a masked language model. The discriminator is trained to discern what tokens have been replaced. This method of pretraining is more efficient than comparable methods like masked language modeling, especially for small models.

Weights are released under the MIT License. Keras model code is released under the Apache 2 License.

Keras and KerasHub can be installed with:

pip install -U -q keras-hub
pip install -U -q keras

Jax, TensorFlow, and Torch come preinstalled in Kaggle Notebooks. For instruction on installing them in another environment see the Keras Getting Started page.

The following model checkpoints are provided by the Keras team. Full code examples for each are available below.