enable --special arg for llama-server (ggml-org#9419)

Co-authored-by: matteo serva <[email protected]>

Author: matteoserva

common/arg.cpp

@@ -818,7 +818,7 @@ gpt_params_context gpt_params_parser_init(gpt_params & params, llama_example ex,
         [](gpt_params & params) {
             params.special = true;
         }
-    ).set_examples({LLAMA_EXAMPLE_MAIN}));
+    ).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_SERVER}));
     add_opt(llama_arg(
         {"-cnv", "--conversation"},
         format(