keras
/

f_net_large_en

Divyasreepat commited on about 4 hours ago

Commit

5495bf4

•

1 Parent(s): ecf35c4

Update README.md with new model card content

Files changed (1) hide show

README.md CHANGED Viewed

@@ -8,7 +8,7 @@ tags:
 - keras
 pipeline_tag: text-classification
 ---
-## Model Overview
 FNet is a set of language models published by Google as part of the paper [FNet: Mixing Tokens with Fourier Transforms](https://arxiv.org/abs/2105.03824). FNet replaces the self-attention of BERT with an unparameterized fourier transform, dramatically lowering the number of trainable parameters in the model. FNet achieves training at 92-97% accuracy of BERT counterparts on GLUE benchmark, with faster training and much smaller saved checkpoints.
 Weights and Keras model code are released under the [Apache 2 License](https://github.com/keras-team/keras-hub/blob/master/LICENSE).
@@ -138,4 +138,4 @@ classifier = keras_hub.models.FNetClassifier.from_preset(
     preprocessor=None,
 )
 classifier.fit(x=features, y=labels, batch_size=2)
-```

 - keras
 pipeline_tag: text-classification
 ---
+### Model Overview
 FNet is a set of language models published by Google as part of the paper [FNet: Mixing Tokens with Fourier Transforms](https://arxiv.org/abs/2105.03824). FNet replaces the self-attention of BERT with an unparameterized fourier transform, dramatically lowering the number of trainable parameters in the model. FNet achieves training at 92-97% accuracy of BERT counterparts on GLUE benchmark, with faster training and much smaller saved checkpoints.
 Weights and Keras model code are released under the [Apache 2 License](https://github.com/keras-team/keras-hub/blob/master/LICENSE).
     preprocessor=None,
 )
 classifier.fit(x=features, y=labels, batch_size=2)
+```