FNetBackbone
classkeras_nlp.models.FNetBackbone(
vocabulary_size,
num_layers,
hidden_dim,
intermediate_dim,
dropout=0.1,
max_sequence_length=512,
num_segments=4,
dtype=None,
**kwargs
)
A FNet encoder network.
This class implements a bi-directional Fourier Transform-based encoder as
described in "FNet: Mixing Tokens with Fourier Transforms".
It includes the embedding lookups and keras_nlp.layers.FNetEncoder
layers,
but not the masked language model or next sentence prediction heads.
The default constructor gives a fully customizable, randomly initialized
FNet encoder with any number of layers and embedding dimensions. To
load preset architectures and weights, use the from_preset()
constructor.
Note: unlike other models, FNet does not take in a "padding_mask"
input,
the "<pad>"
token is handled equivalently to all other tokens in the input
sequence.
Disclaimer: Pre-trained models are provided on an "as is" basis, without warranties or conditions of any kind.
Arguments
max_sequence_length
uses the value from
sequence length. This determines the variable shape for positional
embeddings.keras.mixed_precision.DTypePolicy
. The dtype to use
for model computations and weights. Note that some computations,
such as softmax and layer normalization, will always be done at
float32 precision regardless of dtype.Examples
input_data = {
"token_ids": np.ones(shape=(1, 12), dtype="int32"),
"segment_ids": np.array([[0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0]]),
}
# Pretrained BERT encoder.
model = keras_nlp.models.FNetBackbone.from_preset("f_net_base_en")
model(input_data)
# Randomly initialized FNet encoder with a custom config.
model = keras_nlp.models.FNetBackbone(
vocabulary_size=32000,
num_layers=4,
hidden_dim=256,
intermediate_dim=512,
max_sequence_length=128,
)
model(input_data)
from_preset
methodFNetBackbone.from_preset(preset, load_weights=True, **kwargs)
Instantiate a keras_nlp.models.Backbone
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'
This constructor can be called in one of two ways. Either from the base
class like keras_nlp.models.Backbone.from_preset()
, or from
a model class like keras_nlp.models.GemmaBackbone.from_preset()
.
If calling from the base class, the subclass of the returning object
will be inferred from the config in the preset directory.
For any Backbone
subclass, you can run cls.presets.keys()
to list
all built-in presets available on the class.
Arguments
True
, the weights will be loaded into the
model architecture. If False
, the weights will be randomly
initialized.Examples
# Load a Gemma backbone with pre-trained weights.
model = keras_nlp.models.Backbone.from_preset(
"gemma_2b_en",
)
# Load a Bert backbone with a pre-trained config and random weights.
model = keras_nlp.models.Backbone.from_preset(
"bert_base_en",
load_weights=False,
)
Preset name | Parameters | Description |
---|---|---|
f_net_base_en | 82.86M | 12-layer FNet model where case is maintained. Trained on the C4 dataset. |
f_net_large_en | 236.95M | 24-layer FNet model where case is maintained. Trained on the C4 dataset. |
token_embedding
propertykeras_nlp.models.FNetBackbone.token_embedding
A keras.layers.Embedding
instance for embedding token ids.
This layer embeds integer token ids to the hidden dim of the model.