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

Changed descriptions

Browse source
This commit is contained in:
Maximilian Winter 2024-01-27 07:33:11 +01:00
parent 8f20af4ac6
commit 9d7b7e686c
2 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/server/README.md
View file

@ -30,8 +30,8 @@ Command line options:
- `-cb`, `--cont-batching`: enable continuous batching (a.k.a dynamic batching) (default: disabled) - `-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) - `-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. - `--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-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`: Width of the self extend context size extension. (default: 512) shouldn't be greater than original context size - `--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 ## Build
server is build alongside everything else from the root of the project server is build alongside everything else from the root of the project

4
examples/server/server.cpp
View file

@ -1828,8 +1828,8 @@ static void server_print_usage(const char *argv0, const gpt_params &params,
printf(" --override-kv KEY=TYPE:VALUE\n"); printf(" --override-kv KEY=TYPE:VALUE\n");
printf(" advanced option to override model metadata by key. may be specified multiple times.\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(" 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(" -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(" --grp-attn-w N Width of the self extend context size extension. (default: 512) shouldn't be greater than original context size"); 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"); printf("\n");
} }