Keras 3 API documentation / KerasNLP / Models / DistilBert / DistilBertClassifier model

DistilBertClassifier model

[source]

DistilBertClassifier class

keras_nlp.models.DistilBertClassifier(
    backbone,
    num_classes,
    preprocessor=None,
    activation=None,
    hidden_dim=None,
    dropout=0.2,
    **kwargs
)

An end-to-end DistilBERT model for classification tasks.

This model attaches a classification head to a keras_nlp.model.DistilBertBackbone instance, mapping from the backbone outputs to logits suitable for a classification task. For usage of this model with pre-trained weights, see the from_preset() constructor.

This model can optionally be configured with a preprocessor layer, in which case it will automatically apply preprocessing to raw inputs during fit(), predict(), and evaluate(). This is done by default when creating the model with from_preset().

Disclaimer: Pre-trained models are provided on an "as is" basis, without warranties or conditions of any kind. The underlying model is provided by a third party and subject to a separate license, available here.

Arguments

  • backbone: A keras_nlp.models.DistilBert instance.
  • num_classes: int. Number of classes to predict.
  • preprocessor: A keras_nlp.models.DistilBertPreprocessor or None. If None, this model will not apply preprocessing, and inputs should be preprocessed before calling the model.
  • activation: Optional str or callable. The activation function to use on the model outputs. Set activation="softmax" to return output probabilities. Defaults to None.
  • hidden_dim: int. The size of the pooler layer.
  • dropout: float. The dropout probability value, applied after the first dense layer.

Examples

Raw string data.

features = ["The quick brown fox jumped.", "I forgot my homework."]
labels = [0, 3]

# Use a shorter sequence length.
preprocessor = keras_nlp.models.DistilBertPreprocessor.from_preset(
    "distil_bert_base_en_uncased",
    sequence_length=128,
)
# Pretrained classifier.
classifier = keras_nlp.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.

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_nlp.models.DistilBertClassifier.from_preset(
    "distil_bert_base_en_uncased",
    num_classes=4,
    preprocessor=None,
)
classifier.fit(x=features, y=labels, batch_size=2)

Custom backbone and vocabulary.

features = ["The quick brown fox jumped.", "I forgot my homework."]
labels = [0, 3]
vocab = ["[UNK]", "[CLS]", "[SEP]", "[PAD]", "[MASK]"]
vocab += ["The", "quick", "brown", "fox", "jumped", "."]
tokenizer = keras_nlp.models.DistilBertTokenizer(
    vocabulary=vocab,
)
preprocessor = keras_nlp.models.DistilBertPreprocessor(
    tokenizer=tokenizer,
    sequence_length=128,
)
backbone = keras_nlp.models.DistilBertBackbone(
    vocabulary_size=30552,
    num_layers=4,
    num_heads=4,
    hidden_dim=256,
    intermediate_dim=512,
    max_sequence_length=128,
)
classifier = keras_nlp.models.DistilBertClassifier(
    backbone=backbone,
    preprocessor=preprocessor,
    num_classes=4,
)
classifier.fit(x=features, y=labels, batch_size=2)

[source]

from_preset method

DistilBertClassifier.from_preset()

Instantiate DistilBertClassifier model from preset architecture and weights.

Arguments

  • preset: string. Must be one of "distil_bert_base_en_uncased", "distil_bert_base_en", "distil_bert_base_multi".
  • load_weights: Whether to load pre-trained weights into model. Defaults to True.

Examples

# Load architecture and weights from preset
model = DistilBertClassifier.from_preset("distil_bert_base_en_uncased")

# Load randomly initialized model from preset architecture
model = DistilBertClassifier.from_preset(
    "distil_bert_base_en_uncased",
    load_weights=False
)
Preset name Parameters Description
distil_bert_base_en_uncased 66.36M 6-layer DistilBERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus using BERT as the teacher model.
distil_bert_base_en 65.19M 6-layer DistilBERT model where case is maintained. Trained on English Wikipedia + BooksCorpus using BERT as the teacher model.
distil_bert_base_multi 134.73M 6-layer DistilBERT model where case is maintained. Trained on Wikipedias of 104 languages

backbone property

keras_nlp.models.DistilBertClassifier.backbone

A keras.Model instance providing the backbone sub-model.


preprocessor property

keras_nlp.models.DistilBertClassifier.preprocessor

A keras.layers.Layer instance used to preprocess inputs.