Don't use named args in MHA calls to allow applying pytorch forward hooks to VIT (#6956)

torchvision/models/vision_transformer.py

@@ -110,7 +110,7 @@ class EncoderBlock(nn.Module):
     def forward(self, input: torch.Tensor):
         torch._assert(input.dim() == 3, f"Expected (batch_size, seq_length, hidden_dim) got {input.shape}")
         x = self.ln_1(input)
-        x, _ = self.self_attention(query=x, key=x, value=x, need_weights=False)
+        x, _ = self.self_attention(x, x, x, need_weights=False)
         x = self.dropout(x)
         x = x + input