Keras 3 API documentation / KerasNLP / Models / OPT / OPTBackbone model

OPTBackbone model

[source]

OPTBackbone class

keras_nlp.models.OPTBackbone(
    vocabulary_size,
    num_layers,
    num_heads,
    hidden_dim,
    intermediate_dim,
    dropout=0.1,
    max_sequence_length=2048,
    dtype=None,
    **kwargs
)

An OPT decoder network.

This class implements a Transformer-based decoder model as described in "OPT: Open Pre-trained Transformer Language Models". The default constructor gives a fully customizable, randomly initialized OPT 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 decoder 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 hidden size of the transformer decoder layers.
  • intermediate_dim: int. The output dimension of the first Dense layer in a two-layer feedforward network for each transformer decoder layer.
  • dropout: float. Dropout probability for the Transformer decoder.
  • max_sequence_length: int. The maximum sequence length that this decoder can consume. If None, max_sequence_length uses the value from sequence length. This determines the variable shape for positional embeddings.
  • 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.

Examples

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 OPT decoder
model = keras_nlp.models.OPTBackbone.from_preset("opt_125m_en")
model(input_data)

# Randomly initialized OPT decoder model with a custom config
model = keras_nlp.models.OPTBackbone(
    vocabulary_size=50265,
    num_layers=4,
    num_heads=4,
    hidden_dim=256,
    intermediate_dim=512,
    max_sequence_length=128,
)
model(input_data)

[source]

from_preset method

OPTBackbone.from_preset()

Instantiate OPTBackbone model from preset architecture and weights.

Arguments

  • preset: string. Must be one of "opt_125m_en", "opt_1.3b_en", "opt_2.7b_en", "opt_6.7b_en".
  • load_weights: Whether to load pre-trained weights into model. Defaults to True.

Examples

# Load architecture and weights from preset
model = keras_nlp.models.OPTBackbone.from_preset(
    "opt_125m_en"
)

# Load randomly initialized model from preset architecture
model = keras_nlp.models.OPTBackbone.from_preset(
    "opt_125m_en",
    load_weights=False
)
Preset name Parameters Description
opt_125m_en 125.24M 12-layer OPT model where case in maintained. Trained on BookCorpus, CommonCrawl, Pile, and PushShift.io corpora.
opt_1.3b_en 1.32B 24-layer OPT model where case in maintained. Trained on BookCorpus, CommonCrawl, Pile, and PushShift.io corpora.
opt_2.7b_en 2.70B 32-layer OPT model where case in maintained. Trained on BookCorpus, CommonCrawl, Pile, and PushShift.io corpora.
opt_6.7b_en 6.70B 32-layer OPT model where case in maintained. Trained on BookCorpus, CommonCrawl, Pile, and PushShift.io corpora.

token_embedding property

keras_nlp.models.OPTBackbone.token_embedding

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

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