fix: call super()._init_weights() to match Qwen2Moe convention for transformers v5

modeling_llada2_moe.py

@@ -687,6 +687,7 @@ class LLaDA2MoePreTrainedModel(PreTrainedModel):
     _supports_cache_class = True
 
     def _init_weights(self, module):
+        super()._init_weights(module)
         std = self.config.initializer_range
         if isinstance(module, nn.Linear):
             module.weight.data.normal_(mean=0.0, std=std)