From d1124575e3892204b0e4007b11e11ad28e2fe5cf Mon Sep 17 00:00:00 2001 From: Pierrick HYMBERT Date: Sat, 17 Feb 2024 14:54:33 +0100 Subject: [PATCH] server: fix print usage LF in new --n-predict option --- examples/server/server.cpp | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/examples/server/server.cpp b/examples/server/server.cpp index 7798b8af5..e8c81bc4f 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -1926,14 +1926,14 @@ static void server_print_usage(const char *argv0, const gpt_params ¶ms, printf(" --mmproj MMPROJ_FILE path to a multimodal projector file for LLaVA.\n"); printf(" --log-disable disables logging to a file.\n"); printf("\n"); + printf(" -n, --n-predict maximum tokens to predict (default: %d)\n", params.n_predict); printf(" --override-kv KEY=TYPE:VALUE\n"); printf(" advanced option to override model metadata by key. may be specified multiple times.\n"); printf(" types: int, float, bool. example: --override-kv tokenizer.ggml.add_bos_token=bool:false\n"); 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 values is: llama2, chatml (default %s)", sparams.chat_template.c_str()); - printf(" -n, --n-predict maximum tokens to predict (default: %d)\n", params.n_predict); + printf(" set chat template, possible value is: llama2, chatml (default %s)", sparams.chat_template.c_str()); printf("\n"); }