super initialization

model_utils/efficientnet_config.py

@@ -266,7 +266,7 @@ class EfficientNetConfig(PretrainedConfig):
             norm_layer (Optional[Callable[..., nn.Module]]): Module specifying the normalization layer to use
             last_channel (int): The number of channels on the penultimate layer
         """
-        super().__init__()
+        # super().__init__()
         # _log_api_usage_once(self)
         
         inverted_residual_setting, last_channel = _efficientnet_conf(
@@ -369,6 +369,8 @@ class EfficientNetConfig(PretrainedConfig):
                 init_range = 1.0 / math.sqrt(m.out_features)
                 nn.init.uniform_(m.weight, -init_range, init_range)
                 nn.init.zeros_(m.bias)
+                
+        super().__init__(**kwargs)
 
     def _forward_impl(self, x: Tensor) -> Tensor:
         x = self.features(x)