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 2025-10-20 21:38:49 +01:00
parent 90402c057f
commit 00ddf039b3
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

@ -118,7 +118,7 @@ static bool try_parse_ftype(const std::string & ftype_str_in, llama_ftype & ftyp
[[noreturn]]
static void usage(const char * executable) {
printf("usage: %s [--help] [--allow-requantize] [--leave-output-tensor] [--pure] [--imatrix] [--include-weights] [--exclude-weights] [--target-bpw n]\n", executable);
printf(" [--bpw-state filename] [--keep-bpw-state] [--output-tensor-type] [--token-embedding-type] [--tensor-type] [--prune-layers] [--keep-split] [--override-kv]\n");
printf(" [--keep-bpw-state] [--bpw-state filename] [--output-tensor-type] [--token-embedding-type] [--tensor-type] [--prune-layers] [--keep-split] [--override-kv]\n");
printf(" model-f32.gguf [model-quant.gguf] type [nthreads]\n\n");
printf(" --allow-requantize: allows requantizing tensors that have already been quantized. Warning: This can severely reduce quality compared to quantizing from 16bit or 32bit\n");
printf(" --leave-output-tensor: will leave output.weight un(re)quantized. Increases model size but may also increase quality, especially when requantizing\n");