Fix Multi-GPU trained model export (#14551)

Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

ultralytics/engine/model.py

@@ -588,7 +588,13 @@ class Model(nn.Module):
         self._check_is_pytorch_model()
         from .exporter import Exporter
 
-        custom = {"imgsz": self.model.args["imgsz"], "batch": 1, "data": None, "verbose": False}  # method defaults
+        custom = {
+            "imgsz": self.model.args["imgsz"],
+            "batch": 1,
+            "data": None,
+            "device": None,  # reset to avoid multi-GPU errors
+            "verbose": False,
+        }  # method defaults
         args = {**self.overrides, **custom, **kwargs, "mode": "export"}  # highest priority args on the right
         return Exporter(overrides=args, _callbacks=self.callbacks)(model=self.model)