---
license: apache-2.0
library_name: keras
pipeline_tag: fill-mask
tags:
  - keras
  - kerasformers
  - tf
  - jax
  - pytorch
  - backend-agnostic
  - bert
  - fill-mask
base_model:
  - google-bert/bert-base-uncased
---
# BERT (bert_base_uncased)

A pure [Keras 3](https://keras.io) port of **BERT**, converted from [`google-bert/bert-base-uncased`](https://huggingface.co/google-bert/bert-base-uncased) (Hugging Face Transformers).

The weights are **backend-agnostic**: the same checkpoint loads and runs identically under the JAX, TensorFlow, or PyTorch Keras backend (`KERAS_BACKEND=jax|tensorflow|torch`), via [kerasformers](https://github.com/IMvision12/KerasFormers).

## Usage

```python
from kerasformers.models.bert import BertModel

model = BertModel.from_weights("kerasformers/bert_base_uncased")
```