diff --git a/examples/main/main.cpp b/examples/main/main.cpp index e9478d5..66b7c2d 100644 --- a/examples/main/main.cpp +++ b/examples/main/main.cpp @@ -493,7 +493,7 @@ int main(int argc, char ** argv) { } // In interactive mode, respect the maximum number of tokens and drop back to user input when reached. - if (params.interactive && n_remain <= 0) { + if (params.interactive && n_remain <= 0 && params.n_predict != -1) { n_remain = params.n_predict; is_interacting = true; }