vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

server: document --n-predict

Browse source
This commit is contained in:
Pierrick HYMBERT 2024-02-17 13:18:00 +01:00
parent 5bf2b94dd4
commit cf7137e8d6
2 changed files with 3 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/server/README.md
View file

@ -39,6 +39,7 @@ see https://github.com/ggerganov/llama.cpp/issues/1437
- `--mmproj MMPROJ_FILE`: Path to a multimodal projector file for LLaVA.
- `--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`
- `-n, --n-predict`: Set the maximum tokens to predict (default: -1)
## Build

3
examples/server/server.cpp
View file

@ -1920,7 +1920,8 @@ static void server_print_usage(const char *argv0, const gpt_params &params,
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 valus is: llama2, chatml (default %s)", sparams.chat_template.c_str());
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("\n");
}