XLNetBackbone model

[source]

XLNetBackbone class

keras_hub.models.XLNetBackbone(
    vocabulary_size,
    num_layers,
    num_heads,
    hidden_dim,
    intermediate_dim,
    dropout=0.0,
    activation="gelu",
    kernel_initializer_range=0.02,
    bias_initializer="zeros",
    dtype=None,
    **kwargs
)

XLNet encoder network.

This class implements a XLNet Transformer.

The default constructor gives a fully customizable, randomly initialized XLNet encoder with any number of layers, heads, and embedding dimensions. To load preset architectures and weights, use the from_preset constructor.

Disclaimer: Pre-trained models are provided on an "as is" basis, without warranties or conditions of any kind.

Attributes

• vocabulary_size: int. The size of the token vocabulary.
• num_layers: int. The number of transformer encoder layers.
• num_heads: int, the number of heads in the keras.layers.TwoStreamRelativeAttention layer.
• hidden_dim: int, the size hidden states.
• intermediate_dim: int, the hidden size of feedforward network.
• dropout: float, defaults to 0.0 the dropout value, shared by keras.layers.TwoStreamRelativeAttention and feedforward network.
• activation: string or keras.activations, defaults to "gelu". the activation function of feedforward network.
• kernel_initializer_range: int, defaults to 0.02. The kernel initializer range for the dense and relative attention layers.
• bias_initializer: string or keras.initializers initializer, defaults to "zeros". The bias initializer for the dense and multiheaded relative attention layers.
• dtype: string or 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.

Call arguments

• token_ids: Indices of input sequence tokens in the vocabulary of shape [batch_size, sequence_length].
• segment_ids: Segment token indices to indicate first and second portions of the inputs of shape [batch_size, sequence_length].
• padding_mask: Mask to avoid performing attention on padding token indices of shape [batch_size, sequence_length].

Example

import numpy as np
from keras_hub.src.models import XLNetBackbone

input_data = {
    "token_ids": np.array(
        [460, 5272, 1758, 4905, 9, 4, 3], shape=(1, 7),
    ),
    "segment_ids": np.array(
        [0, 0, 0, 0, 0, 0, 2], shape=(1, 7),
    ),
    "padding_mask": np.array(
        [1, 1, 1, 1, 1, 1, 1], shape=(1, 7)
    ),
}

# Randomly initialized XLNet encoder with a custom config
model = keras_hub.models.XLNetBackbone(
    vocabulary_size=32000,
    num_layers=12,
    num_heads=12,
    hidden_dim=768,
    intermediate_dim=3072,
)
output = model(input_data)

[source]

from_preset method

XLNetBackbone.from_preset(preset, load_weights=True, **kwargs)

Instantiate a keras_hub.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:

1. a built-in preset identifier like 'bert_base_en'
2. a Kaggle Models handle like 'kaggle://user/bert/keras/bert_base_en'
3. a Hugging Face handle like 'hf://user/bert_base_en'
4. a path to a local preset directory like './bert_base_en'

This constructor can be called in one of two ways. Either from the base class like keras_hub.models.Backbone.from_preset(), or from a model class like keras_hub.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

• preset: string. A built-in preset identifier, a Kaggle Models handle, a Hugging Face handle, or a path to a local directory.
• load_weights: bool. If 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_hub.models.Backbone.from_preset(
    "gemma_2b_en",
)

# Load a Bert backbone with a pre-trained config and random weights.
model = keras_hub.models.Backbone.from_preset(
    "bert_base_en",
    load_weights=False,
)

token_embedding property

keras_hub.models.XLNetBackbone.token_embedding

A keras.layers.Embedding instance for embedding token ids.

This layer embeds integer token ids to the hidden dim of the model.