Fix loading models from cache (#820)

Author: eaidova

optimum/intel/openvino/modeling_base.py

@@ -132,7 +132,11 @@ def fix_op_names_duplicates(model: openvino.runtime.Model):
 
         if isinstance(file_name, str):
             file_name = Path(file_name)
-        model = core.read_model(file_name) if not file_name.suffix == ".onnx" else convert_model(file_name)
+        model = (
+            core.read_model(file_name.resolve(), file_name.with_suffix(".bin").resolve())
+            if not file_name.suffix == ".onnx"
+            else convert_model(file_name)
+        )
         if file_name.suffix == ".onnx":
             model = fix_op_names_duplicates(model)  # should be called during model conversion to IR