CoolFace
Modelpublic

keras/bert_base_en_uncased

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes7downloads
Model Card

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

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 nameParametersDescription
bert_tiny_en_uncased4.39M2-layer BERT model where all input is lowercased.
bert_small_en_uncased28.76M4-layer BERT model where all input is lowercased.
bert_medium_en_uncased41.37M8-layer BERT model where all input is lowercased.
bert_base_en_uncased109.48M12-layer BERT model where all input is lowercased.
bert_base_en108.31M12-layer BERT model where case is maintained.
bert_base_zh102.27M12-layer BERT model. Trained on Chinese Wikipedia.
bert_base_multi177.85M12-layer BERT model where case is maintained.
bert_large_en_uncased335.14M24-layer BERT model where all input is lowercased.
bert_large_en333.58M24-layer BERT model where case is maintained.
bert_tiny_en_uncased_sst2 4.39Mhe berttinyen_uncased backbone model fine-tuned on the SST-2 sentiment analysis dataset.

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_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.

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_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]

# 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.

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_base_en_uncased",
    num_classes=4,
    preprocessor=None,
)
classifier.fit(x=features, y=labels, batch_size=2)