BloomBackbone 模型

[source]

BloomBackbone class

keras_nlp.models.BloomBackbone(
    vocabulary_size,
    num_layers,
    num_heads,
    hidden_dim,
    intermediate_dim,
    dropout=0.0,
    layer_norm_epsilon=1e-05,
    dtype=None,
    **kwargs
)

A BLOOM decoder network.

This network implements a Transformer-based decoder network, BigScience Language Open-science Open-access Multilingual (BLOOM), as descriped in "BLOOM: A 176B-Parameter Open-Access Multilingual Language Model".

The default constructor gives a fully customizable, randomly initialized Bloom model 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. The underlying model is provided by a third party and subject to a separate license, available here.

Arguments

• vocabulary_size: int. The size of the token vocabulary.
• num_layers: int. The number of transformer layers.
• num_heads: int. The number of attention heads for each transformer. The hidden size must be divisible by the number of attention heads.
• hidden_dim: int. The dimensionality of the embeddings and hidden states.
• intermediate_dim: int. The output dimension of the first Dense layer in the MLP network of each transformer.
• dropout: float. Dropout probability for the Transformer decoder.
• layer_norm_epsilon: float. Epsilon for the layer normalization layers in the transformer decoder.
• 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.

Example

input_data = {
    "token_ids": np.ones(shape=(1, 12), dtype="int32"),
    "padding_mask": np.array([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0]]),
}

# Pretrained BLOOM decoder.
model = keras_nlp.models.BloomBackbone.from_preset("bloom_560m_multi")
model(input_data)

# Randomly initialized BLOOM decoder with a custom config.
model = keras_nlp.models.BloomBackbone(
    vocabulary_size=10,
    num_layers=2,
    num_heads=2,
    hidden_dim=32,
    intermediate_dim=32*4,
    dropout=0.0,
    layer_norm_epsilon=1e-5,
)
model(input_data)

[source]

from_preset method

BloomBackbone.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:

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_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

• 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_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,
)

token_embedding property

keras_nlp.models.BloomBackbone.token_embedding

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

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

[source]

enable_lora method

BloomBackbone.enable_lora(rank)

Enable Lora on the backbone.

Calling this method will freeze all weights on the backbone, while enabling Lora on the query & value EinsumDense layers of the attention layers.