From 9d7b7e686cc766c5fa0e9622f2b35730d36e0d25 Mon Sep 17 00:00:00 2001 From: Maximilian Winter Date: Sat, 27 Jan 2024 07:33:11 +0100 Subject: [PATCH] Changed descriptions --- examples/server/README.md | 4 ++-- examples/server/server.cpp | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/examples/server/README.md b/examples/server/README.md index d5626dad4..1c92a2041 100644 --- a/examples/server/README.md +++ b/examples/server/README.md @@ -30,8 +30,8 @@ Command line options: - `-cb`, `--cont-batching`: enable continuous batching (a.k.a dynamic batching) (default: disabled) - `-spf FNAME`, `--system-prompt-file FNAME` Set a file to load "a system prompt (initial prompt of all slots), this is useful for chat applications. [See more](#change-system-prompt-on-runtime) - `--mmproj MMPROJ_FILE`: Path to a multimodal projector file for LLaVA. -- `--grp-attn-n`: Extend context size through self extend. Extend context size n-times (default: 1), used together with `--grp-attn-w` -- `--grp-attn-w`: Width of the self extend context size extension. (default: 512) shouldn't be greater than original context size +- `--grp-attn-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` +- `--grp-attn-w`: Set the group attention width to extend context size through self-extend(default: 512), used together with group attention factor `--grp-attn-n` ## Build server is build alongside everything else from the root of the project diff --git a/examples/server/server.cpp b/examples/server/server.cpp index ff3b01876..bf0220cff 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -1828,8 +1828,8 @@ static void server_print_usage(const char *argv0, const gpt_params ¶ms, 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(" --grp-attn-n N Extend context size through self extend. Extend context size n-times (default: 1), used together with `--grp-attn-w`"); - printf(" --grp-attn-w N Width of the self extend context size extension. (default: 512) shouldn't be greater than original context size"); + 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("\n"); }