[NvTensorRTRTX EP]Disable Fast GELU operator in base model used for NV EP Unit Tests (microsoft#25323)

### Description
Remove fast_gelu operator from the base model created in NV TRT RTX EP
unit tests.



### Motivation and Context
The operator was added in the model to partition the model into
subgraphs which can be assigned to NV TRT RTX EP and CUDA EP, which
supports fast_gelu. But CUDA EP is not built when building ORT with NV
TRT RTX EP hence the unit tests fail with unsupported op error.

@ishwar-raut1 @ankan-ban

Author: keshavv27

onnxruntime/test/providers/nv_tensorrt_rtx/nv_basic_test.cc

@@ -322,7 +322,7 @@ TEST(NvExecutionProviderTest, ContextEmbedAndReloadDataDynamic) {
   std::string graph_name = "test";
   std::vector<int> dims = {1, -1, -1};
 
-  CreateBaseModel(model_name, graph_name, dims, true);
+  CreateBaseModel(model_name, graph_name, dims);
 
   auto env = Ort::Env();
   auto logging_level = OrtLoggingLevel::ORT_LOGGING_LEVEL_WARNING;
@@ -371,7 +371,7 @@ TYPED_TEST(NvExecutionProviderTest, IOTypeTests) {
   std::string graph_name = "test" + dtype_name;
   std::vector<int> dims = {1, -1, -1};
 
-  CreateBaseModel(model_name, graph_name, dims, true);
+  CreateBaseModel(model_name, graph_name, dims);
 
   auto env = Ort::Env();
   auto logging_level = OrtLoggingLevel::ORT_LOGGING_LEVEL_WARNING;