DistilBertClassifier
classkeras_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
keras_nlp.models.DistilBert
instance.keras_nlp.models.DistilBertPreprocessor
or None
. If
None
, this model will not apply preprocessing, and inputs should
be preprocessed before calling the model.str
or callable. The
activation function to use on the model outputs. Set
activation="softmax"
to return output probabilities.
Defaults to None
.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)
from_preset
methodDistilBertClassifier.from_preset(preset, load_weights=True, **kwargs)
Instantiate a keras_nlp.models.Task
from a model preset.
A preset is a directory of configs, weights and other file assets used
to save and load a pre-trained model. The preset
can be passed as a
one of:
'bert_base_en'
'kaggle://user/bert/keras/bert_base_en'
'hf://user/bert_base_en'
'./bert_base_en'
For any Task
subclass, you can run cls.presets.keys()
to list all
built-in presets available on the class.
This constructor can be called in one of two ways. Either from a task
specific base class like keras_nlp.models.CausalLM.from_preset()
, or
from a model class like keras_nlp.models.BertClassifier.from_preset()
.
If calling from the a base class, the subclass of the returning object
will be inferred from the config in the preset directory.
Arguments
True
, the weights will be loaded into the
model architecture. If False
, the weights will be randomly
initialized.Examples
# Load a Gemma generative task.
causal_lm = keras_nlp.models.CausalLM.from_preset(
"gemma_2b_en",
)
# Load a Bert classification task.
model = keras_nlp.models.Classifier.from_preset(
"bert_base_en",
num_classes=2,
)
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
propertykeras_nlp.models.DistilBertClassifier.backbone
A keras_nlp.models.Backbone
model with the core architecture.
preprocessor
propertykeras_nlp.models.DistilBertClassifier.preprocessor
A keras_nlp.models.Preprocessor
layer used to preprocess input.