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 2025-12-25 17:44:43 +00:00
parent b6d718a4a6
commit 3be3b1ef87
No known key found for this signature in database
GPG Key ID: E7875815A3230993
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tools/quantize/quantize.cpp
View File

@ -136,7 +136,7 @@ static void usage(const char * executable) {
printf(" Advanced option to automatically select quantization types to achieve a total bits per weight (bpw) target\n");
printf(" --no-importance: distribute bpw budget equitably across all tensors\n");
printf(" Advanced option to disable assigning more bpw budget to important tensors. It may increase quality for some models\n");
printf(" --keep-bpw-state: save the bpw computations to <architecture>-<model hash>.bpw_state\n");
printf(" --keep-bpw-state: save the bpw computations to <model name>-<model hash>.bpw_state\n");
printf(" --bpw-state: file name to use instead of default\n");
printf(" --keep-split: will generate quantized model in the same shards as input\n");
printf(" --override-kv KEY=TYPE:VALUE\n");