---
library_name: keras-hub
license: apache-2.0
language:
- en
tags:
- text-classification
---
### Model Overview
BERT (Bidirectional Encoder Representations from Transformers) is a set of language models published by Google. They are intended for classification and embedding of text, not for text-generation. See the model card below for benchmarks, data sources, and intended use cases.

Weights and Keras model code are released under the [Apache 2 License](https://github.com/keras-team/keras-hub/blob/master/LICENSE).

## Links

* [Bert Quickstart Notebook](https://www.kaggle.com/code/matthewdwatson/bert-quickstart)
* [Bert API Documentation](https://keras.io/api/keras_hub/models/bert/)
* [Bert Model Card](https://github.com/google-research/bert/blob/master/README.md)
* [KerasHub Beginner Guide](https://keras.io/guides/keras_hub/getting_started/)
* [KerasHub Model Publishing Guide](https://keras.io/guides/keras_hub/upload/)

## Installation

Keras and KerasHub can be installed with:

```
pip install -U -q keras-hub
pip install -U -q keras>=3
```

Jax, TensorFlow, and Torch come preinstalled in Kaggle Notebooks. For instruction on installing them in another environment see the [Keras Getting Started](https://keras.io/getting_started/) page.

## Presets

The following model checkpoints are provided by the Keras team. Full code examples for each are available below.

| Preset name            | Parameters | Description                                                                                     |
|------------------------|------------|-------------------------------------------------------------------------------------------------|
| `bert_tiny_en_uncased`   | 4.39M      | 2-layer BERT model where all input is lowercased.   |
| `bert_small_en_uncased`  | 28.76M     | 4-layer BERT model where all input is lowercased.   |
| `bert_medium_en_uncased` | 41.37M     | 8-layer BERT model where all input is lowercased.   |
| `bert_base_en_uncased`   | 109.48M    | 12-layer BERT model where all input is lowercased.  |
| `bert_base_en`           | 108.31M    | 12-layer BERT model where case is maintained.  |
| `bert_base_zh`           | 102.27M    | 12-layer BERT model. Trained on Chinese Wikipedia.                                              |
| `bert_base_multi`        | 177.85M    | 12-layer BERT model where case is maintained. |
| `bert_large_en_uncased`  | 335.14M    | 24-layer BERT model where all input is lowercased. |
| `bert_large_en`          | 333.58M    | 24-layer BERT model where case is maintained. |

## Example Usage
```python
import keras
import keras_hub
import numpy as np
```

Raw string data.
```python
features = ["The quick brown fox jumped.", "I forgot my homework."]
labels = [0, 3]

# Pretrained classifier.
classifier = keras_hub.models.BertClassifier.from_preset(
    "bert_small_en_uncased",
    num_classes=4,
)
classifier.fit(x=features, y=labels, batch_size=2)
classifier.predict(x=features, batch_size=2)

# Re-compile (e.g., with a new learning rate).
classifier.compile(
    loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
    optimizer=keras.optimizers.Adam(5e-5),
    jit_compile=True,
)
# Access backbone programmatically (e.g., to change `trainable`).
classifier.backbone.trainable = False
# Fit again.
classifier.fit(x=features, y=labels, batch_size=2)
```

Preprocessed integer data.
```python
features = {
    "token_ids": np.ones(shape=(2, 12), dtype="int32"),
    "segment_ids": np.array([[0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0]] * 2),
    "padding_mask": np.array([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0]] * 2),
}
labels = [0, 3]

# Pretrained classifier without preprocessing.
classifier = keras_hub.models.BertClassifier.from_preset(
    "bert_small_en_uncased",
    num_classes=4,
    preprocessor=None,
)
classifier.fit(x=features, y=labels, batch_size=2)
```

## Example Usage with Hugging Face URI

```python
import keras
import keras_hub
import numpy as np
```

Raw string data.
```python
features = ["The quick brown fox jumped.", "I forgot my homework."]
labels = [0, 3]

# Pretrained classifier.
classifier = keras_hub.models.BertClassifier.from_preset(
    "hf://keras/bert_small_en_uncased",
    num_classes=4,
)
classifier.fit(x=features, y=labels, batch_size=2)
classifier.predict(x=features, batch_size=2)

# Re-compile (e.g., with a new learning rate).
classifier.compile(
    loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
    optimizer=keras.optimizers.Adam(5e-5),
    jit_compile=True,
)
# Access backbone programmatically (e.g., to change `trainable`).
classifier.backbone.trainable = False
# Fit again.
classifier.fit(x=features, y=labels, batch_size=2)
```

Preprocessed integer data.
```python
features = {
    "token_ids": np.ones(shape=(2, 12), dtype="int32"),
    "segment_ids": np.array([[0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0]] * 2),
    "padding_mask": np.array([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0]] * 2),
}
labels = [0, 3]

# Pretrained classifier without preprocessing.
classifier = keras_hub.models.BertClassifier.from_preset(
    "hf://keras/bert_small_en_uncased",
    num_classes=4,
    preprocessor=None,
)
classifier.fit(x=features, y=labels, batch_size=2)
```