Added tokens to identify if is loading or ready

examples/main/main.cpp

@@ -242,7 +242,8 @@ int main(int argc, char ** argv) {
                " - Press Ctrl+C to interject at any time.\n"
 #endif
                " - Press Return to return control to LLaMa.\n"
-               " - If you want to submit another line, end your input in '\\'.\n\n");
+               " - If you want to submit another line, end your input in '\\'.\n"
+               "[model ready]\n");
         is_interacting = params.interactive_start;
     }
 

llama.cpp

@@ -931,6 +931,7 @@ static void llama_model_load_internal(
 
         fprintf(stderr, "%s: mem required  = %7.2f MB (+ %7.2f MB per state)\n", __func__,
                 mem_required / 1024.0 / 1024.0, mem_required_state / 1024.0 / 1024.0);
+        fprintf(stderr, "[model loading]\n");
     }
 
     // create the ggml context