ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-25 07:34:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add the --custom-q option to the help

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-03-06 18:38:32 +02:00
parent 480c2265cd
commit d29f8d3d40
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View File

@@ -144,6 +144,7 @@ static void usage(const char * executable) {
printf(" --exclude-weights tensor_name: use importance matrix for this/these tensor(s)\n");
printf(" --output-tensor-type ggml_type: use this ggml_type for the output.weight tensor.\n");
printf(" --token-embedding-type ggml_type: use this ggml_type for the token_embd.weight tensor.\n\n");
printf(" --custom-q regex1=type1,regex2=type2...: use this to specify custom quantization type rules.\n\n");
printf("Additional specific tensor quantization types used in the custom quant scheme 'CQS (default is Q2_K):\n");
printf(" --attn-q-type ggml_type: use this ggml_type for the attn_q.weight tensor.\n");
printf(" --attn-k-type ggml_type: use this ggml_type for the attn_k.weight tensor.\n");