Update modeling_llava_qwen2.py

modeling_llava_qwen2.py

@@ -538,13 +538,13 @@ class SigLipVisionTower(nn.Module):
                 image_forward_out = self.vision_tower(image.to(device=self.device, dtype=self.dtype).unsqueeze(0),
                                                       output_hidden_states=True)
                 image_feature = image_forward_out.hidden_states[-1].to(image.dtype)
-                assert image_features.shape[-2] == 729
+                # assert image_features.shape[-2] == 729
                 image_features.append(image_feature)
         else:
             image_forward_outs = self.vision_tower(images.to(device=self.device, dtype=self.dtype),
                                                    output_hidden_states=True)
             image_features = image_forward_outs.hidden_states[-1].to(images.dtype)
-            assert image_features.shape[-2] == 729
+            # assert image_features.shape[-2] == 729
 
         return image_features