diff --git a/examples/common.cpp b/examples/common.cpp
index 3fdee868d..55e977171 100644
--- a/examples/common.cpp
+++ b/examples/common.cpp
@@ -493,7 +493,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     fprintf(stderr, "  -n N, --n-predict N   number of tokens to predict (default: %d, -1 = infinity)\n", params.n_predict);
     fprintf(stderr, "  -c N, --ctx-size N    size of the prompt context (default: %d)\n", params.n_ctx);
     fprintf(stderr, "  -b N, --batch-size N  batch size for prompt processing (default: %d)\n", params.n_batch);
-    fprintf(stderr, "  -gqa N, --gqa N       grouped-query attention factor (TEMP!!! use 7 for LLaMAv2 70B) (default: %d)\n", params.n_gqa);
+    fprintf(stderr, "  -gqa N, --gqa N       grouped-query attention factor (TEMP!!! use 8 for LLaMAv2 70B) (default: %d)\n", params.n_gqa);
     fprintf(stderr, "  --top-k N             top-k sampling (default: %d, 0 = disabled)\n", params.top_k);
     fprintf(stderr, "  --top-p N             top-p sampling (default: %.1f, 1.0 = disabled)\n", (double)params.top_p);
     fprintf(stderr, "  --tfs N               tail free sampling, parameter z (default: %.1f, 1.0 = disabled)\n", (double)params.tfs_z);