diff --git a/src/transformers/models/qwen2_moe/modeling_qwen2_moe.py b/src/transformers/models/qwen2_moe/modeling_qwen2_moe.py
index a529dcdb559..7f81c331ccc 100644
--- a/src/transformers/models/qwen2_moe/modeling_qwen2_moe.py
+++ b/src/transformers/models/qwen2_moe/modeling_qwen2_moe.py
@@ -281,7 +281,7 @@ class Qwen2MoeAttention(nn.Module):
 
         self.hidden_size = config.hidden_size
         self.num_heads = config.num_attention_heads
-        self.head_dim = self.hidden_size // self.num_heads
+        self.head_dim = getattr(config, "head_dim", config.hidden_size // config.num_attention_heads)
         self.num_key_value_heads = config.num_key_value_heads
         self.num_key_value_groups = self.num_heads // self.num_key_value_heads
         self.max_position_embeddings = config.max_position_embeddings