kaira.models.generic.IdentityModel

Inheritance diagram for IdentityModel

class kaira.models.generic.IdentityModel

Bases: BaseModel

Identity Model.

This model returns the input tensor without any modifications. It can be used as a baseline model or as a placeholder in model pipelines.

Example

>>> model = IdentityModel()
>>> x = torch.randn(5, 10)
>>> output = model(x)
>>> assert torch.allclose(x, output)

Methods

__init__	Initialize the IdentityModel.
forward	Forward pass through the model.
from_config	Create model instance from configuration.
from_hydra_config	Create model from Hydra DictConfig.
from_pretrained_config	Create model from Hugging Face PretrainedConfig.

__init__()

Initialize the IdentityModel.

forward(x: Tensor, *args: Any, **kwargs: Any) → Tensor

Forward pass through the model.

Parameters:

• x (torch.Tensor) – The input tensor.

• *args – Additional positional arguments

• **kwargs – Additional keyword arguments

Returns:

The input tensor (unchanged).

Return type:

torch.Tensor

classmethod from_config(config, **kwargs)

Create model instance from configuration.

Parameters:

• config – Configuration object (PretrainedConfig, DictConfig, or dict)

• **kwargs – Additional parameters to override config

Returns:

Model instance

classmethod from_hydra_config(config: DictConfig, **kwargs)

Create model from Hydra DictConfig.

Parameters:

• config – Hydra configuration

• **kwargs – Additional parameters

Returns:

Model instance

classmethod from_pretrained_config(config: PretrainedConfig, **kwargs)

Create model from Hugging Face PretrainedConfig.

Parameters:

• config – PretrainedConfig instance

• **kwargs – Additional parameters

Returns:

Model instance