easydel.modules.siglip.configuration_siglip

class easydel.modules.siglip.configuration_siglip.SiglipConfig(text_config=None, vision_config=None, **kwargs)

Bases: EasyDeLBaseConfig

[SiglipConfig] is the configuration class to store the configuration of a [SiglipModel]. It is used to instantiate a Siglip model according to the specified arguments, defining the text model and vision model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the Siglip [google/siglip-base-patch16-224](https://huggingface.co/google/siglip-base-patch16-224) architecture.

Configuration objects inherit from [EasyDeLBaseConfig] and can be used to control the model outputs. Read the documentation from [EasyDeLBaseConfig] for more information.

Parameters

• text_config (dict, optional) – Dictionary of configuration options used to initialize [SiglipTextConfig].

• vision_config (dict, optional) – Dictionary of configuration options used to initialize [SiglipVisionConfig].

• kwargs (optional) – Dictionary of keyword arguments.

classmethod from_text_vision_configs(text_config: SiglipTextConfig, vision_config: SiglipVisionConfig, **kwargs)

Instantiate a [SiglipConfig] (or a derived class) from siglip text model configuration and siglip vision model configuration.

Returns

An instance of a configuration object

Return type

[SiglipConfig]

get_partition_rules(*args, **kwargs)

Get the partition rules for the SigLIP model parameters for use with distributed training.

These rules define how parameters should be partitioned across multiple devices when using techniques like Fully Sharded Data Parallelism (FSDP), Sharded Parallelism (SP), and Tensor Parallelism (TP). Each rule consists of a regex pattern for matching parameter names and a corresponding PartitionSpec.

Returns

A tuple of tuples where each inner tuple contains:

• A regex pattern matching parameter names

• A PartitionSpec object specifying how to partition matching parameters

Return type

tuple

model_type: str = 'siglip'

The model type identifier used to determine which model configuration this represents. This is set to “siglip” to identify this as the main configuration for the SigLIP model.

sub_configs: dict[str, 'PretrainedConfig'] = {'text_config': <class 'easydel.modules.siglip.configuration_siglip.SiglipTextConfig'>, 'vision_config': <class 'easydel.modules.siglip.configuration_siglip.SiglipVisionConfig'>}

A dictionary that maps configuration keys to their respective configuration classes. This enables the SiglipConfig to manage both text and vision components through separate configurations while maintaining them as part of a single unified model.

class easydel.modules.siglip.configuration_siglip.SiglipTextConfig(vocab_size=32000, hidden_size=768, intermediate_size=3072, num_hidden_layers=12, num_attention_heads=12, max_position_embeddings=64, hidden_act='gelu_pytorch_tanh', layer_norm_eps=1e-06, attention_dropout=0.0, pad_token_id=1, bos_token_id=49406, eos_token_id=49407, projection_size=None, **kwargs)

Bases: EasyDeLBaseConfig

Configuration objects inherit from [EasyDeLBaseConfig] and can be used to control the model outputs. Read the documentation from [EasyDeLBaseConfig] for more information.

Parameters

• vocab_size (int, optional, defaults to 32000) – Vocabulary size of the Siglip text model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling [SiglipModel].

• hidden_size (int, optional, defaults to 768) – Dimensionality of the encoder layers and the pooler layer.

• intermediate_size (int, optional, defaults to 3072) – Dimensionality of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder.

• num_hidden_layers (int, optional, defaults to 12) – Number of hidden layers in the Transformer encoder.

• num_attention_heads (int, optional, defaults to 12) – Number of attention heads for each attention layer in the Transformer encoder.

• max_position_embeddings (int, optional, defaults to 64) – The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048).

• hidden_act (str or function, optional, defaults to “gelu_pytorch_tanh”) – The non-linear activation function (function or string) in the encoder and pooler. If string, “gelu”, “relu”, “selu” and “gelu_new” “quick_gelu” are supported.

• layer_norm_eps (float, optional, defaults to 1e-06) – The epsilon used by the layer normalization layers.

• attention_dropout (float, optional, defaults to 0.0) – The dropout ratio for the attention probabilities.

• pad_token_id (int, optional, defaults to 1) – The id of the padding token in the vocabulary.

• bos_token_id (int, optional, defaults to 49406) – The id of the beginning-of-sequence token in the vocabulary.

• eos_token_id (int, optional, defaults to 49407) – The id of the end-of-sequence token in the vocabulary.

• projection_size (int, optional, defaults to hidden_size) – The size of the projection head.

Example:

```python >>> from transformers import SiglipTextConfig, SiglipTextModel

>>> # Initializing a SiglipTextConfig with google/siglip-base-patch16-224 style configuration
>>> configuration = SiglipTextConfig()

>>> # Initializing a SiglipTextModel (with random weights) from the google/siglip-base-patch16-224 style configuration
>>> model = SiglipTextModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```

base_config_key: str = 'text_config'

get_partition_rules(*args, **kwargs)

Get the partition rules for the model. :returns: The partition rules. :rtype: tp.Tuple[tp.Tuple[str, PartitionSpec]]

model_type: str = 'siglip_text_model'

class easydel.modules.siglip.configuration_siglip.SiglipVisionConfig(hidden_size=768, intermediate_size=3072, num_hidden_layers=12, num_attention_heads=12, num_channels=3, image_size=224, patch_size=16, hidden_act='gelu_pytorch_tanh', layer_norm_eps=1e-06, attention_dropout=0.0, **kwargs)

Bases: EasyDeLBaseConfig

Configuration objects inherit from [EasyDeLBaseConfig] and can be used to control the model outputs. Read the documentation from [EasyDeLBaseConfig] for more information.

Parameters

• hidden_size (int, optional, defaults to 768) – Dimensionality of the encoder layers and the pooler layer.

• intermediate_size (int, optional, defaults to 3072) – Dimensionality of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder.

• num_hidden_layers (int, optional, defaults to 12) – Number of hidden layers in the Transformer encoder.

• num_attention_heads (int, optional, defaults to 12) – Number of attention heads for each attention layer in the Transformer encoder.

• num_channels (int, optional, defaults to 3) – Number of channels in the input images.

• image_size (int, optional, defaults to 224) – The size (resolution) of each image.

• patch_size (int, optional, defaults to 16) – The size (resolution) of each patch.

• hidden_act (str or function, optional, defaults to “gelu_pytorch_tanh”) – The non-linear activation function (function or string) in the encoder and pooler. If string, “gelu”, “relu”, “selu” and “gelu_new” “quick_gelu” are supported.

• layer_norm_eps (float, optional, defaults to 1e-06) – The epsilon used by the layer normalization layers.

• attention_dropout (float, optional, defaults to 0.0) – The dropout ratio for the attention probabilities.

base_config_key: str = 'vision_config'

get_partition_rules(*args, **kwargs)

Get the partition rules for the model. :returns: The partition rules. :rtype: tp.Tuple[tp.Tuple[str, PartitionSpec]]

model_type: str = 'siglip_vision_model'