@@ -818,7 +818,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
818
818
printf (" \n " );
819
819
printf (" options:\n " );
820
820
printf (" -h, --help show this help message and exit\n " );
821
- printf (" --version show version and build info\n " );
821
+ printf (" --version show version and build info\n " );
822
822
printf (" -i, --interactive run in interactive mode\n " );
823
823
printf (" --interactive-first run in interactive mode and wait for input right away\n " );
824
824
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) {
915
915
printf (" number of layers to store in VRAM\n " );
916
916
printf (" -ngld N, --n-gpu-layers-draft N\n " );
917
917
printf (" number of layers to store in VRAM for the draft model\n " );
918
- printf (" -ts SPLIT --tensor-split SPLIT\n " );
918
+ printf (" -ts SPLIT, --tensor-split SPLIT\n " );
919
919
printf (" how to split tensors across multiple GPUs, comma-separated list of proportions, e.g. 3,1\n " );
920
920
printf (" -mg i, --main-gpu i the GPU to use for scratch and small tensors\n " );
921
921
#ifdef GGML_USE_CUBLAS
@@ -950,7 +950,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
950
950
printf (" --override-kv KEY=TYPE:VALUE\n " );
951
951
printf (" advanced option to override model metadata by key. may be specified multiple times.\n " );
952
952
printf (" types: int, float, bool. example: --override-kv tokenizer.ggml.add_bos_token=bool:false\n " );
953
- printf (" -stc N --print-token-count N\n " );
953
+ printf (" -stc N, --print-token-count N\n " );
954
954
printf (" print token count every N tokens (default: %d)\n " , params.n_print );
955
955
printf (" \n " );
956
956
#ifndef LOG_DISABLE_LOGS
0 commit comments