cli: enable jinja by default (ggml-org#17911)

* cli: enable jinja by default

* Update common/arg.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

Author: ngxson

common/arg.cpp

@@ -762,12 +762,6 @@ bool common_arg_utils::is_autoy(const std::string & value) {
 }
 
 common_params_context common_params_parser_init(common_params & params, llama_example ex, void(*print_usage)(int, char **)) {
-    // default values specific to example
-    // note: we place it here instead of inside server.cpp to allow llama-gen-docs to pick it up
-    if (ex == LLAMA_EXAMPLE_SERVER) {
-        params.use_jinja = true;
-    }
-
     params.use_color = tty_can_use_colors();
 
     // load dynamic backends
@@ -2623,14 +2617,14 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
     ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_MODELS_AUTOLOAD"));
     add_opt(common_arg(
         {"--jinja"},
-        string_format("use jinja template for chat (default: %s)\n", params.use_jinja ? "enabled" : "disabled"),
+        string_format("use jinja template for chat (default: %s)", params.use_jinja ? "enabled" : "disabled"),
         [](common_params & params) {
             params.use_jinja = true;
         }
     ).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_MTMD}).set_env("LLAMA_ARG_JINJA"));
     add_opt(common_arg(
         {"--no-jinja"},
-        string_format("disable jinja template for chat (default: %s)\n", params.use_jinja ? "enabled" : "disabled"),
+        string_format("disable jinja template for chat (default: %s)", params.use_jinja ? "disabled" : "enabled"),
         [](common_params & params) {
             params.use_jinja = false;
         }

common/common.h

@@ -464,7 +464,7 @@ struct common_params {
     std::string public_path   = "";                                                                         // NOLINT
     std::string api_prefix    = "";                                                                         // NOLINT
     std::string chat_template = "";                                                                         // NOLINT
-    bool use_jinja = false;                                                                                 // NOLINT
+    bool use_jinja = true;                                                                                  // NOLINT
     bool enable_chat_template = true;
     common_reasoning_format reasoning_format = COMMON_REASONING_FORMAT_DEEPSEEK;
     int reasoning_budget = -1;

tools/completion/completion.cpp

@@ -86,6 +86,10 @@ static void sigint_handler(int signo) {
 int main(int argc, char ** argv) {
     common_params params;
     g_params = &params;
+
+    // disable jinja by default
+    params.use_jinja = false;
+
     if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_COMPLETION, print_usage)) {
         return 1;
     }

tools/mtmd/mtmd-cli.cpp

@@ -270,6 +270,7 @@ int main(int argc, char ** argv) {
     ggml_time_init();
 
     common_params params;
+    params.use_jinja = false;   // disable jinja by default
     params.sampling.temp = 0.2; // lower temp by default for better quality
 
     if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_MTMD, show_additional_info)) {