diff --git a/examples/server/oai.hpp b/examples/server/oai.hpp
index c0c1f521e..2199df237 100644
--- a/examples/server/oai.hpp
+++ b/examples/server/oai.hpp
@@ -21,8 +21,8 @@ inline static json oaicompat_completion_params_parse(
     json llama_params;
     bool using_chatml = chat_template == "chatml";
     std::string formatted_prompt = using_chatml
-        ? format_chatml(body["messages"])  // OpenAI 'messages' to chatml
-        : format_mistral(body["messages"]); // OpenAI 'messages' to mistral format
+        ? format_chatml(body["messages"])  // OpenAI 'messages' to chatml (with <|im_start|>,...)
+        : format_llama2(body["messages"]); // OpenAI 'messages' to llama2 (with [INST],...)
 
     llama_params["__oaicompat"] = true;
 
diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index 2183abcb1..d4161ed92 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -1861,7 +1861,7 @@ static void server_print_usage(const char *argv0, const gpt_params &params,
     printf("  -gan N, --grp-attn-n N    set the group attention factor to extend context size through self-extend(default: 1=disabled), used together with group attention width `--grp-attn-w`");
     printf("  -gaw N, --grp-attn-w N    set the group attention width to extend context size through self-extend(default: 512), used together with group attention factor `--grp-attn-n`");
     printf("  --chat-template FORMAT_NAME");
-    printf("                            set chat template, possible valus is: mistral, chatml (default %s)", sparams.chat_template.c_str());
+    printf("                            set chat template, possible valus is: llama2, chatml (default %s)", sparams.chat_template.c_str());
     printf("\n");
 }
 
diff --git a/examples/server/utils.hpp b/examples/server/utils.hpp
index 5ec743fb8..b1623c737 100644
--- a/examples/server/utils.hpp
+++ b/examples/server/utils.hpp
@@ -167,7 +167,7 @@ static T json_value(const json &body, const std::string &key, const T &default_v
         : default_value;
 }
 
-inline std::string format_mistral(std::vector<json> messages)
+inline std::string format_llama2(std::vector<json> messages)
 {
     std::ostringstream output;
     bool is_inside_turn = false;
@@ -190,7 +190,7 @@ inline std::string format_mistral(std::vector<json> messages)
         }
     }
 
-    LOG_VERBOSE("format_mistral", {{"text", output.str()}});
+    LOG_VERBOSE("format_llama2", {{"text", output.str()}});
 
     return output.str();
 }