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

5.2 KiB

MobileBERT

Overview

The MobileBERT model was proposed in MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices by Zhiqing Sun, Hongkun Yu, Xiaodan Song, Renjie Liu, Yiming Yang, and Denny Zhou. It's a bidirectional transformer based on the BERT model, which is compressed and accelerated using several approaches.

The abstract from the paper is the following:

Natural Language Processing (NLP) has recently achieved great success by using huge pre-trained models with hundreds of millions of parameters. However, these models suffer from heavy model sizes and high latency such that they cannot be deployed to resource-limited mobile devices. In this paper, we propose MobileBERT for compressing and accelerating the popular BERT model. Like the original BERT, MobileBERT is task-agnostic, that is, it can be generically applied to various downstream NLP tasks via simple fine-tuning. Basically, MobileBERT is a thin version of BERT_LARGE, while equipped with bottleneck structures and a carefully designed balance between self-attentions and feed-forward networks. To train MobileBERT, we first train a specially designed teacher model, an inverted-bottleneck incorporated BERT_LARGE model. Then, we conduct knowledge transfer from this teacher to MobileBERT. Empirical studies show that MobileBERT is 4.3x smaller and 5.5x faster than BERT_BASE while achieving competitive results on well-known benchmarks. On the natural language inference tasks of GLUE, MobileBERT achieves a GLUEscore o 77.7 (0.6 lower than BERT_BASE), and 62 ms latency on a Pixel 4 phone. On the SQuAD v1.1/v2.0 question answering task, MobileBERT achieves a dev F1 score of 90.0/79.2 (1.5/2.1 higher than BERT_BASE).

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

Usage tips

  • MobileBERT is a model with absolute position embeddings so it's usually advised to pad the inputs on the right rather than the left.
  • MobileBERT is similar to BERT and therefore relies on the masked language modeling (MLM) objective. It is therefore efficient at predicting masked tokens and at NLU in general, but is not optimal for text generation. Models trained with a causal language modeling (CLM) objective are better in that regard.

Resources

MobileBertConfig

autodoc MobileBertConfig

MobileBertTokenizer

autodoc MobileBertTokenizer

MobileBertTokenizerFast

autodoc MobileBertTokenizerFast

MobileBert specific outputs

autodoc models.mobilebert.modeling_mobilebert.MobileBertForPreTrainingOutput

autodoc models.mobilebert.modeling_tf_mobilebert.TFMobileBertForPreTrainingOutput

MobileBertModel

autodoc MobileBertModel - forward

MobileBertForPreTraining

autodoc MobileBertForPreTraining - forward

MobileBertForMaskedLM

autodoc MobileBertForMaskedLM - forward

MobileBertForNextSentencePrediction

autodoc MobileBertForNextSentencePrediction - forward

MobileBertForSequenceClassification

autodoc MobileBertForSequenceClassification - forward

MobileBertForMultipleChoice

autodoc MobileBertForMultipleChoice - forward

MobileBertForTokenClassification

autodoc MobileBertForTokenClassification - forward

MobileBertForQuestionAnswering

autodoc MobileBertForQuestionAnswering - forward

TFMobileBertModel

autodoc TFMobileBertModel - call

TFMobileBertForPreTraining

autodoc TFMobileBertForPreTraining - call

TFMobileBertForMaskedLM

autodoc TFMobileBertForMaskedLM - call

TFMobileBertForNextSentencePrediction

autodoc TFMobileBertForNextSentencePrediction - call

TFMobileBertForSequenceClassification

autodoc TFMobileBertForSequenceClassification - call

TFMobileBertForMultipleChoice

autodoc TFMobileBertForMultipleChoice - call

TFMobileBertForTokenClassification

autodoc TFMobileBertForTokenClassification - call

TFMobileBertForQuestionAnswering

autodoc TFMobileBertForQuestionAnswering - call