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 / BERT

BERT

Models, tokenizers, and preprocessing layers for BERT, as described in "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding".

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

BertTokenizer

  • BertTokenizer class
  • from_preset method

BertBackbone model

  • BertBackbone class
  • from_preset method
  • token_embedding property

BertTextClassifier model

  • BertTextClassifier class
  • from_preset method
  • backbone property
  • preprocessor property

BertTextClassifierPreprocessor layer

  • BertTextClassifierPreprocessor class
  • from_preset method
  • tokenizer property

BertMaskedLM model

  • BertMaskedLM class
  • from_preset method
  • backbone property
  • preprocessor property

BertMaskedLMPreprocessor layer

  • BertMaskedLMPreprocessor class
  • from_preset method
  • tokenizer property
BERT
BertTokenizer
BertBackbone model
BertTextClassifier model
BertTextClassifierPreprocessor layer
BertMaskedLM model
BertMaskedLMPreprocessor layer
Terms | Privacy