MetaCLIP2TextEncoder

[source]

MetaCLIP2TextEncoder class

keras_hub.models.MetaCLIP2TextEncoder(
    vocabulary_size,
    embedding_dim,
    hidden_dim,
    num_layers,
    num_heads,
    intermediate_dim,
    intermediate_activation="quick_gelu",
    intermediate_output_index=None,
    max_sequence_length=77,
    dtype=None,
    name=None,
    **kwargs
)

MetaCLIP 2 text encoder.

Arguments

• vocabulary_size: int. The size of the token vocabulary.
• embedding_dim: int. The output dimension of the embedding layer.
• hidden_dim: int. The size of the transformer hidden state at the end of each transformer layer.
• num_layers: int. The number of transformer layers.
• num_heads: int. The number of attention heads for each transformer.
• intermediate_dim: int. The output dimension of the first Dense layer in a two-layer feedforward network for each transformer.
• intermediate_activation: activation function. The activation that is used for the first Dense layer in a two-layer feedforward network for each transformer. Defaults to "quick_gelu".
• intermediate_output_index: optional int. The index of the intermediate output. If specified, the output will include an additional "intermediate_output" key.
• max_sequence_length: int. The maximum sequence length that this encoder can consume. Defaults to 77. Used for pooling. Defaults to 2.
• dtype: string or keras.mixed_precision.DTypePolicy. The dtype to use for the models computations and weights. Note that some computations, such as softmax and layer normalization will always be done at float32 precision regardless of dtype.

[source]

from_preset method

MetaCLIP2TextEncoder.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 ModelScope handle like 'modelscope://user/bert_base_en'
5. 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,
)