Replace tensor.norm() with decomposed version for CLIP executorch e…

…xport (huggingface#32887)

* Replace .norm() with decomposed version for executorch export

* [run_slow] clip

src/transformers/models/clip/modeling_clip.py

@@ -67,6 +67,17 @@ def clip_loss(similarity: torch.Tensor) -> torch.Tensor:
     return (caption_loss + image_loss) / 2.0
 
 
+def _get_vector_norm(tensor: torch.Tensor) -> torch.Tensor:
+    """
+    This method is equivalent to tensor.norm(p=2, dim=-1, keepdim=True) and used to make
+    model `executorch` exportable. See issue https://github.com/pytorch/executorch/issues/3566
+    """
+    square_tensor = torch.pow(tensor, 2)
+    sum_tensor = torch.sum(square_tensor, dim=-1, keepdim=True)
+    normed_tensor = torch.pow(sum_tensor, 0.5)
+    return normed_tensor
+
+
 @dataclass
 class CLIPVisionModelOutput(ModelOutput):
     """
@@ -1313,8 +1324,8 @@ def forward(
         text_embeds = self.text_projection(text_embeds)
 
         # normalized features
-        image_embeds = image_embeds / image_embeds.norm(p=2, dim=-1, keepdim=True)
-        text_embeds = text_embeds / text_embeds.norm(p=2, dim=-1, keepdim=True)
+        image_embeds = image_embeds / _get_vector_norm(image_embeds)
+        text_embeds = text_embeds / _get_vector_norm(text_embeds)
 
         # cosine similarity as logits
         logit_scale = self.logit_scale.exp()