transformers/docs/source/en/model_doc/fnet.md

FNet

Overview

The FNet model was proposed in FNet: Mixing Tokens with Fourier Transforms by James Lee-Thorp, Joshua Ainslie, Ilya Eckstein, Santiago Ontanon. The model replaces the self-attention layer in a BERT model with a fourier transform which returns only the real parts of the transform. The model is significantly faster than the BERT model because it has fewer parameters and is more memory efficient. The model achieves about 92-97% accuracy of BERT counterparts on GLUE benchmark, and trains much faster than the BERT model. The abstract from the paper is the following:

We show that Transformer encoder architectures can be sped up, with limited accuracy costs, by replacing the self-attention sublayers with simple linear transformations that "mix" input tokens. These linear mixers, along with standard nonlinearities in feed-forward layers, prove competent at modeling semantic relationships in several text classification tasks. Most surprisingly, we find that replacing the self-attention sublayer in a Transformer encoder with a standard, unparameterized Fourier Transform achieves 92-97% of the accuracy of BERT counterparts on the GLUE benchmark, but trains 80% faster on GPUs and 70% faster on TPUs at standard 512 input lengths. At longer input lengths, our FNet model is significantly faster: when compared to the "efficient" Transformers on the Long Range Arena benchmark, FNet matches the accuracy of the most accurate models, while outpacing the fastest models across all sequence lengths on GPUs (and across relatively shorter lengths on TPUs). Finally, FNet has a light memory footprint and is particularly efficient at smaller model sizes; for a fixed speed and accuracy budget, small FNet models outperform Transformer counterparts.

This model was contributed by gchhablani. The original code can be found here.

Usage tips

The model was trained without an attention mask as it is based on Fourier Transform. The model was trained with maximum sequence length 512 which includes pad tokens. Hence, it is highly recommended to use the same maximum sequence length for fine-tuning and inference.

Resources

• Text classification task guide
• Token classification task guide
• Question answering task guide
• Masked language modeling task guide
• Multiple choice task guide

FNetConfig

autodoc FNetConfig

FNetTokenizer

autodoc FNetTokenizer - build_inputs_with_special_tokens - get_special_tokens_mask - create_token_type_ids_from_sequences - save_vocabulary

FNetTokenizerFast

autodoc FNetTokenizerFast

FNetModel

autodoc FNetModel - forward

FNetForPreTraining

autodoc FNetForPreTraining - forward

FNetForMaskedLM

autodoc FNetForMaskedLM - forward

FNetForNextSentencePrediction

autodoc FNetForNextSentencePrediction - forward

FNetForSequenceClassification

autodoc FNetForSequenceClassification - forward

FNetForMultipleChoice

autodoc FNetForMultipleChoice - forward

FNetForTokenClassification

autodoc FNetForTokenClassification - forward

FNetForQuestionAnswering

autodoc FNetForQuestionAnswering - forward