more versatile model loading

pytorch_pretrained_bert/modeling.py

@@ -606,7 +606,9 @@ class BertPreTrainedModel(nn.Module):
             for name, child in module._modules.items():
                 if child is not None:
                     load(child, prefix + name + '.')
-        start_prefix = 'bert.' if not hasattr(model, 'bert') and any(s.startwith('bert.') for s in state_dict.keys()) else ''
+        start_prefix = ''
+        if not hasattr(model, 'bert') and any(s.startswith('bert.') for s in state_dict.keys()):
+            start_prefix = 'bert.'
         load(model, prefix=start_prefix)
         if len(missing_keys) > 0:
             logger.info("Weights of {} not initialized from pretrained model: {}".format(