src/peft/tuners/loha/layer.py [257:291]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        adapter_name: str = "default",
        r: int = 0,
        alpha: float = 0.0,
        rank_dropout: float = 0.0,
        module_dropout: float = 0.0,
        use_effective_conv2d: bool = False,
        init_weights: bool = True,
        **kwargs,
    ):
        super().__init__(base_layer)

        # Create adapter and set it active
        self._active_adapter = adapter_name
        self.update_layer(
            adapter_name, r, alpha, rank_dropout, module_dropout, init_weights, use_effective_conv2d, **kwargs
        )

    def _get_delta_activations(
        self, adapter_name: str, input: torch.Tensor, *args: Any, **kwargs: Any
    ) -> torch.Tensor:
        delta_weight = self.get_delta_weight(adapter_name)
        input = self._cast_input_dtype(input, delta_weight.dtype)
        # don't add bias here, because the bias is already included in the output of the base_layer
        base_layer = self.get_base_layer()
        return F.conv2d(
            input,
            delta_weight,
            stride=base_layer.stride,
            padding=base_layer.padding,
            dilation=base_layer.dilation,
            groups=base_layer.groups,
        )

    def __repr__(self) -> str:
        rep = super().__repr__()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/peft/tuners/lokr/layer.py [323:357]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        adapter_name: str = "default",
        r: int = 0,
        alpha: float = 0.0,
        rank_dropout: float = 0.0,
        module_dropout: float = 0.0,
        use_effective_conv2d: bool = False,
        init_weights: bool = True,
        **kwargs,
    ):
        super().__init__(base_layer)

        # Create adapter and set it active
        self._active_adapter = adapter_name
        self.update_layer(
            adapter_name, r, alpha, rank_dropout, module_dropout, init_weights, use_effective_conv2d, **kwargs
        )

    def _get_delta_activations(
        self, adapter_name: str, input: torch.Tensor, *args: Any, **kwargs: Any
    ) -> torch.Tensor:
        delta_weight = self.get_delta_weight(adapter_name)
        input = self._cast_input_dtype(input, delta_weight.dtype)
        # don't add bias here, because the bias is already included in the output of the base_layer
        base_layer = self.get_base_layer()
        return F.conv2d(
            input,
            delta_weight,
            stride=base_layer.stride,
            padding=base_layer.padding,
            dilation=base_layer.dilation,
            groups=base_layer.groups,
        )

    def __repr__(self) -> str:
        rep = super().__repr__()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -