See our collection for all versions of BERT.

Run BERT with Keras 3: JAX, PyTorch, or TensorFlow

kerasformers/bert_base_cased

Paper: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (arXiv:1810.04805) · HF Papers

BERT is Google's bidirectional transformer text encoder, pretrained with masked LM and next-sentence prediction. WordPiece tokenizer; mask token [MASK]. Uncased variants lower-case the input; cased variants preserve case.

For more details on the model, please go to the upstream model card.

Pure-Keras 3 conversion of google-bert/bert-base-cased for kerasformers. One implementation runs unmodified on TensorFlow / Torch / JAX.

This is a fill-mask / encoder checkpoint (BertMaskedLM, base cased). Task heads (sequence/token classify, QA, NSP, …) load via hf: fine-tunes.

✨ Quick start (fill-mask)

import os
os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"

from kerasformers.models.bert import BertMaskedLM, BertTokenizer

mlm = BertMaskedLM.from_weights("kerasformers/bert_base_cased")
tokenizer = BertTokenizer.from_weights("kerasformers/bert_base_cased")

inputs = tokenizer("The capital of France is [MASK].")
logits = mlm(inputs)  # (1, L, vocab_size)
mask = int((inputs["input_ids"][0] == tokenizer.mask_token_id).argmax())
print(tokenizer.ids_to_tokens[int(logits[0, mask].argmax())])

Load any BERT variant the same way with from_weights("kerasformers/<variant>"):

Variant	Hub	Casing
`bert_base_uncased`	`kerasformers/bert_base_uncased`	uncased
`bert_large_uncased`	`kerasformers/bert_large_uncased`	uncased
`bert_base_cased`	`kerasformers/bert_base_cased`	cased
`bert_large_cased`	`kerasformers/bert_large_cased`	cased

Tips

Set KERAS_BACKEND before importing Keras / kerasformers.
Prefer BertTokenizer.from_weights(...) so WordPiece casing matches.
Use [MASK] (not <mask>).
See BERT docs and Loading Weights.
Community / upstream safetensors still work via the hf: prefix, e.g. BertMaskedLM.from_weights("hf:google-bert/bert-base-cased").