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.
Links
- Bert Quickstart Notebook
- Bert API Documentation
- Bert Model Card
- KerasHub Beginner Guide
- KerasHub Model Publishing Guide
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 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. |
bert_tiny_en_uncased_sst2 | 4.39M | he bert_tiny_en_uncased backbone model fine-tuned on the SST-2 sentiment analysis dataset. |
Example Usage
import keras
import keras_hub
import numpy as np
Raw string data.
features = ["The quick brown fox jumped.", "I forgot my homework."]
labels = [0, 3]
# Pretrained classifier.
classifier = keras_hub.models.BertClassifier.from_preset(
"bert_base_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.
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_base_en_uncased",
num_classes=4,
preprocessor=None,
)
classifier.fit(x=features, y=labels, batch_size=2)
Example Usage with Hugging Face URI
import keras
import keras_hub
import numpy as np
Raw string data.
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_base_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.
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_base_en_uncased",
num_classes=4,
preprocessor=None,
)
classifier.fit(x=features, y=labels, batch_size=2)