---
library_name: keras-hub
license: apache-2.0
language:
- en
tags:
- text-classification
pipeline_tag: text-classification
---
### Model Overview
DistilBert is a set of language models published by HuggingFace. They are efficient, distilled version of BERT, and 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

* [DistilBert Quickstart Notebook](https://www.kaggle.com/code/matthewdwatson/distilbert-quickstart)
* [DistilBert API Documentation](https://keras.io/api/keras_hub/models/distil_bert/)
* [DistilBert Model Card](https://huggingface.co/distilbert/distilbert-base-uncased)
* [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                                            |
|-----------------------------|------------|--------------------------------------------------------|
| distil_bert_base_en_uncased | 66.36M     | 6-layer model where all input is lowercased.           |
| distil_bert_base_en         | 65.19M     | 6-layer model where case is maintained.                |
| distil_bert_base_multi      | 134.73M    | 6-layer multi-linguage 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]

# Use a shorter sequence length.
preprocessor = keras_hub.models.DistilBertPreprocessor.from_preset(
    "distil_bert_base_en_uncased",
    sequence_length=128,
)
# Pretrained classifier.
classifier = keras_hub.models.DistilBertClassifier.from_preset(
    "distil_bert_base_en_uncased",
    num_classes=4,
    preprocessor=preprocessor,
)
classifier.fit(x=features, y=labels, 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"),
    "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.DistilBertClassifier.from_preset(
    "distil_bert_base_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]

# Use a shorter sequence length.
preprocessor = keras_hub.models.DistilBertPreprocessor.from_preset(
    "hf://keras/distil_bert_base_en_uncased",
    sequence_length=128,
)
# Pretrained classifier.
classifier = keras_hub.models.DistilBertClassifier.from_preset(
    "hf://keras/distil_bert_base_en_uncased",
    num_classes=4,
    preprocessor=preprocessor,
)
classifier.fit(x=features, y=labels, 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"),
    "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.DistilBertClassifier.from_preset(
    "hf://keras/distil_bert_base_en_uncased",
    num_classes=4,
    preprocessor=None,
)
classifier.fit(x=features, y=labels, batch_size=2)
```