diff --git a/common/common.cpp b/common/common.cpp
index a7ef4565c..0c04c0b9b 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -1636,7 +1636,7 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
         params.cvector_negative_file = argv[i];
         return true;
     }
-    if (arg == "--num-completions") {
+    if (arg == "--completions") {
         if (++i >= argc) {
             invalid_param = true;
             return true;
@@ -1986,7 +1986,7 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
     options.push_back({ "control-vector-generator", "--positive-file FNAME",   "positive prompts file, one prompt per line (default: '%s')", params.cvector_positive_file.c_str() });
     options.push_back({ "control-vector-generator", "--negative-file FNAME",   "negative prompts file, one prompt per line (default: '%s')", params.cvector_negative_file.c_str() });
     options.push_back({ "control-vector-generator", "--completions-file FNAME","completions file (default: '%s')", params.cvector_completions_file.c_str() });
-    options.push_back({ "control-vector-generator", "--num-completions N",     "number of lines of completions file to use (default: %d)", params.n_completions });
+    options.push_back({ "control-vector-generator", "--completions N",         "number of lines of completions file to use (default: %d)", params.n_completions });
     options.push_back({ "control-vector-generator", "--batch-pca N",           "batch size used for PCA. Larger batch runs faster, but uses more memory (default: %d)", params.n_pca_batch });
     options.push_back({ "control-vector-generator", "--iter-pca N",            "number of iterations used for PCA (default: %d)", params.n_pca_iterations });
 
diff --git a/examples/control-vector-generator/README.md b/examples/control-vector-generator/README.md
index 1ccb05d78..fd89dfa3b 100644
--- a/examples/control-vector-generator/README.md
+++ b/examples/control-vector-generator/README.md
@@ -17,7 +17,7 @@ Example:
 ./control-vector-generator -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99
 
 # With advanced options
-./control-vector-generator -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99 --num-completions 128 --pca-iter 2000 --batch-pca 100
+./control-vector-generator -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99 --completions 128 --pca-iter 2000 --batch-pca 100
 
 # To see help message
 ./control-vector-generator -h
diff --git a/examples/control-vector-generator/control-vector-generator.cpp b/examples/control-vector-generator/control-vector-generator.cpp
index 96a0e7958..136f78974 100644
--- a/examples/control-vector-generator/control-vector-generator.cpp
+++ b/examples/control-vector-generator/control-vector-generator.cpp
@@ -22,7 +22,7 @@
 
 
 //////////////////////////////////////////////////
-
+// utils
 
 template <class Iter>
 static std::string tokens_to_str(llama_context * ctx, Iter begin, Iter end) {
@@ -34,6 +34,15 @@ static std::string tokens_to_str(llama_context * ctx, Iter begin, Iter end) {
     return ret;
 }
 
+static void print_usage(int argc, char ** argv, const gpt_params & params) {
+    gpt_params_print_usage(argc, argv, params);
+
+    printf("\nexample usage:\n");
+    printf("\n    CPU only:   %s -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf\n", argv[0]);
+    printf("\n    with GPU:   %s -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99\n", argv[0]);
+    printf("\n    advanced:   %s -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99 --completions 128 --pca-iter 2000 --batch-pca 100\n", argv[0]);
+    printf("\n");
+}
 
 //////////////////////////////////////////////////
 
@@ -384,7 +393,7 @@ int main(int argc, char ** argv) {
     gpt_params params;
 
     if (!gpt_params_parse(argc, argv, params)) {
-        gpt_params_print_usage(argc, argv, params);
+        print_usage(argc, argv, params);
         return 1;
     }