Function _init_weights

model_zigma.py:512–541

(
    module,
    n_layer,
    initializer_range=0.02,  # Now only used for embedding layer.
    rescale_prenorm_residual=True,
    n_residuals_per_layer=1,  # Change to 2 if we have MLP
)

def _init_weights(
    module,
    n_layer,
    initializer_range=0.02,  # Now only used for embedding layer.
    rescale_prenorm_residual=True,
    n_residuals_per_layer=1,  # Change to 2 if we have MLP
):
    if isinstance(module, nn.Linear):
        if module.bias is not None:
            if not getattr(module.bias, "_no_reinit", False):
                nn.init.zeros_(module.bias)
    elif isinstance(module, nn.Embedding):
        nn.init.normal_(module.weight, std=initializer_range)

    if rescale_prenorm_residual:
        # Reinitialize selected weights subject to the OpenAI GPT-2 Paper Scheme:
        #   > A modified initialization which accounts for the accumulation on the residual path with model depth. Scale
        #   > the weights of residual layers at initialization by a factor of 1/√N where N is the # of residual layers.
        #   >   -- GPT-2 :: https://openai.com/blog/better-language-models/
        #
        # Reference (Megatron-LM): https://github.com/NVIDIA/Megatron-LM/blob/main/megatron/model/gpt_model.py
        for name, p in module.named_parameters():
            if name in ["out_proj.weight", "fc2.weight"]:
                # Special Scaled Initialization --> There are 2 Layer Norms per Transformer Block
                # Following Pytorch init, except scale by 1/sqrt(2 * n_layer)
                # We need to reinit p since this code could be called multiple times
                # Having just p *= scale would repeatedly scale it down
                nn.init.kaiming_uniform_(p, a=math.sqrt(5))
                with torch.no_grad():
                    p /= math.sqrt(n_residuals_per_layer * n_layer)


class ZigMa(nn.Module):