About Keras Getting started Developer guides Keras 3 API documentation Models API Layers API Callbacks API Ops API Optimizers Metrics Losses Data loading Built-in small datasets Keras Applications Mixed precision Multi-device distribution RNG API Utilities KerasTuner KerasCV KerasNLP KerasHub Pretrained Models Models API Tokenizers Preprocessing Layers Modeling Layers Samplers Metrics Keras 2 API documentation Code examples KerasTuner: Hyperparameter Tuning KerasHub: Pretrained Models KerasCV: Computer Vision Workflows KerasNLP: Natural Language Workflows
► Keras 3 API documentation / KerasHub / Pretrained Models / DistilBERT

DistilBERT

Models, tokenizers, and preprocessing layers for DistilBERT, as described in "DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter".

For a full list of available presets, see the models page.

DistilBertTokenizer

  • DistilBertTokenizer class
  • from_preset method

DistilBertBackbone model

  • DistilBertBackbone class
  • from_preset method
  • token_embedding property

DistilBertTextClassifier model

  • DistilBertTextClassifier class
  • from_preset method
  • backbone property
  • preprocessor property

DistilBertTextClassifierPreprocessor layer

  • DistilBertTextClassifierPreprocessor class
  • from_preset method
  • tokenizer property

DistilBertMaskedLM model

  • DistilBertMaskedLM class
  • from_preset method
  • backbone property
  • preprocessor property

DistilBertMaskedLMPreprocessor layer

  • DistilBertMaskedLMPreprocessor class
  • from_preset method
  • tokenizer property
DistilBERT
DistilBertTokenizer
DistilBertBackbone model
DistilBertTextClassifier model
DistilBertTextClassifierPreprocessor layer
DistilBertMaskedLM model
DistilBertMaskedLMPreprocessor layer
Terms | Privacy