happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

add example to --help

This commit is contained in:
ddh0 2026-02-11 15:36:42 -06:00
parent 966b21a981
commit 07f882bbbb
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tools/quantize/quantize.cpp
View File

@ -158,7 +158,8 @@ static void usage(const char * executable) {
printf(" override model metadata by key in the quantized model. may be specified multiple times.\n"); printf(" override model metadata by key in the quantized model. may be specified multiple times.\n");
printf(" WARNING: this is an advanced option, use with care.\n"); printf(" WARNING: this is an advanced option, use with care.\n");
printf(" --dry-run\n"); printf(" --dry-run\n");
printf(" calculate and show the final quantization size without performing quantization\n\n"); printf(" calculate and show the final quantization size without performing quantization\n");
printf(" example: llama-quantize --dry-run model-f32.gguf Q4_K\n\n");
printf("note: --include-weights and --exclude-weights cannot be used together\n\n"); printf("note: --include-weights and --exclude-weights cannot be used together\n\n");
printf("-----------------------------------------------------------------------------\n"); printf("-----------------------------------------------------------------------------\n");
printf(" allowed quantization types\n"); printf(" allowed quantization types\n");