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

Update usage

This commit is contained in:
Ed Addario 2025-08-19 10:43:51 +01:00
parent 4d9491141b
commit cfec4048ab
No known key found for this signature in database
GPG Key ID: E7875815A3230993
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
tools/quantize/quantize.cpp
View File

@ -132,6 +132,7 @@ static void usage(const char * executable) {
printf(" Advanced option to selectively quantize tensors. May be specified multiple times.\n");
printf(" --prune-layers L0,L1,L2...comma-separated list of layer numbers to prune from the model\n");
printf(" Advanced option to remove all tensors from the given layers\n");
printf(" --target-bpw: target bits per weight (bpw). Must be a positive number between 0.0 and 8.0 \n");
printf(" --keep-split: will generate quantized model in the same shards as input\n");
printf(" --override-kv KEY=TYPE:VALUE\n");
printf(" Advanced option to override model metadata by key in the quantized model. May be specified multiple times.\n");