[PT] Fix aten::add decomposition for i4 weights (#29525)

**Details:** Fix aten::add decomposition for i4 weights

Cherry-pick of #29511

**Ticket:** 164397

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

Author: rkazants

src/frontends/pytorch/src/op/add.cpp

@@ -67,7 +67,7 @@ OutputVector translate_add_common(const NodeContext& context, bool inplace) {
 
     if (alpha.get_node_shared_ptr()) {
         auto converted_alpha = ComplexTypeMark::convert_like(context, alpha, rhs);
-        rhs = ComplexTypeMark::mul(context, rhs, converted_alpha);
+        rhs = ComplexTypeMark::mul(context, converted_alpha, rhs);
     }
 
     auto add = ComplexTypeMark::add(context, lhs, rhs);

src/frontends/pytorch/src/op/sub.cpp

@@ -38,7 +38,7 @@ OutputVector translate_sub_common(const NodeContext& context, bool inplace) {
         auto alpha = context.get_input(2);
         auto casted_alpha = ComplexTypeMark::convert_like(context, alpha, y);
 
-        y = ComplexTypeMark::mul(context, y, casted_alpha);
+        y = ComplexTypeMark::mul(context, casted_alpha, y);
     }
 
     auto sub = ComplexTypeMark::sub(context, x, y);

tests/layer_tests/py_frontend_tests/test_torch_frontend.py

@@ -455,7 +455,7 @@ def forward(self, x):
     converted_model = fe.convert(input_model)
     assert converted_model
     assert [n.get_type_name() for n in converted_model.get_ordered_ops()] == [
-        "Parameter", "Convert", "Convert", "Cos", "Relu", "Constant", "Convert", "Multiply", "Add", "Result"]
+        "Parameter", "Convert", "Convert", "Cos", "Constant", "Convert", "Relu", "Multiply", "Add", "Result"]
 
     converted_model = convert_model(model, example_input=(
         torch.randn(100),), extension=[ModuleExtension(CosModel, "aten::sin"), ModuleExtension(model.relu_module, "aten::tan")])