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

cleanup of cleanup

This commit is contained in:
ddh0 2026-02-03 22:50:08 -06:00
parent 51385adf89
commit 8001bb3bf0
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
tools/quantize/quantize.cpp
View File

@ -123,16 +123,16 @@ static void usage(const char * executable) {
printf(" [--prune-layers] [--keep-split] [--override-kv]\n");
printf(" model-f32.gguf [model-quant.gguf] type [nthreads]\n\n");
printf(" --allow-requantize\n");
printf(" allows requantizing tensors that have already been quantized.\n");
printf(" WARNING: this can severely reduce quality compared to quantizing from 16bit\n");
printf(" or 32bit!\n");
printf(" allow requantizing tensors that have already been quantized\n");
printf(" WARNING: this can severely reduce quality compared to quantizing\n");
printf(" from 16bit or 32bit!\n");
printf(" --leave-output-tensor\n");
printf(" will leave output.weight un(re)quantized. Increases model size but may\n");
printf(" also increase quality, especially when requantizing\n");
printf(" leave output.weight un(re)quantized\n");
printf(" increases model size but may also increase quality, especially when requantizing\n");
printf(" --pure\n");
printf(" disable k-quant mixtures and quantize all tensors to the same type\n");
printf(" --imatrix file_name\n");
printf(" use data in file_name as importance matrix for quant optimizations");
printf(" use data in file_name as importance matrix for quant optimizations\n");
printf(" --include-weights tensor_name\n");
printf(" use importance matrix for this/these tensor(s)\n");
printf(" --exclude-weights tensor_name\n");
@ -145,7 +145,7 @@ static void usage(const char * executable) {
printf(" quantize this tensor to this ggml_type\n");
printf(" this is an advanced option to selectively quantize tensors. may be specified multiple times.\n");
printf(" example: --tensor-type attn_q=q8_0\n");
printf(" --tensor-type-file tensor_type.txt\n");
printf(" --tensor-type-file tensor_types.txt\n");
printf(" list of tensors to quantize to a specific ggml_type\n");
printf(" this is an advanced option to selectively quantize a long list of tensors.\n");
printf(" the file should use the same format as above, separated by spaces or newlines.\n");
@ -153,7 +153,7 @@ static void usage(const char * executable) {
printf(" comma-separated list of layer numbers to prune from the model\n");
printf(" WARNING: this is an advanced option, use with care.\n");
printf(" --keep-split\n");
printf(" will generate quantized model in the same shards as input\n");
printf(" generate quantized model in the same shards as input\n");
printf(" --override-kv KEY=TYPE:VALUE\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\n");