Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-11 21:10:24 +01:00
Code Issues Packages Projects Releases Wiki Activity

common : streamline the formatting of help (#4890)

Browse Source 
* common : streamline the formatting of help

- Separate alternative parameters by a comma

- Do not indent `--version` differently

* Update common/common.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
howlger 2024-01-12 12:05:32 +01:00 committed by GitHub
parent 2d00741e12
commit 4315a94366
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
common/common.cpp
View File

@ -818,7 +818,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf("\n"); printf("\n");
printf("options:\n"); printf("options:\n");
printf(" -h, --help show this help message and exit\n"); printf(" -h, --help show this help message and exit\n");
printf(" --version show version and build info\n"); printf(" --version show version and build info\n");
printf(" -i, --interactive run in interactive mode\n"); printf(" -i, --interactive run in interactive mode\n");
printf(" --interactive-first run in interactive mode and wait for input right away\n"); printf(" --interactive-first run in interactive mode and wait for input right away\n");
printf(" -ins, --instruct run in instruction mode (use with Alpaca models)\n"); printf(" -ins, --instruct run in instruction mode (use with Alpaca models)\n");
@ -915,7 +915,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" number of layers to store in VRAM\n"); printf(" number of layers to store in VRAM\n");
printf(" -ngld N, --n-gpu-layers-draft N\n"); printf(" -ngld N, --n-gpu-layers-draft N\n");
printf(" number of layers to store in VRAM for the draft model\n"); printf(" number of layers to store in VRAM for the draft model\n");
printf(" -ts SPLIT --tensor-split SPLIT\n"); printf(" -ts SPLIT, --tensor-split SPLIT\n");
printf(" how to split tensors across multiple GPUs, comma-separated list of proportions, e.g. 3,1\n"); printf(" how to split tensors across multiple GPUs, comma-separated list of proportions, e.g. 3,1\n");
printf(" -mg i, --main-gpu i the GPU to use for scratch and small tensors\n"); printf(" -mg i, --main-gpu i the GPU to use for scratch and small tensors\n");
#ifdef GGML_USE_CUBLAS #ifdef GGML_USE_CUBLAS
@ -950,7 +950,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, 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(" -stc N --print-token-count N\n"); printf(" -ptc N, --print-token-count N\n");
printf(" print token count every N tokens (default: %d)\n", params.n_print); printf(" print token count every N tokens (default: %d)\n", params.n_print);
printf("\n"); printf("\n");
#ifndef LOG_DISABLE_LOGS #ifndef LOG_DISABLE_LOGS