From 467a882fd2e5b6172897b49aa45aa29bd3f27685 Mon Sep 17 00:00:00 2001 From: Kawrakow <48489457+ikawrakow@users.noreply.github.com> Date: Sun, 14 Jan 2024 16:21:12 +0200 Subject: Add ability to use importance matrix for all k-quants (#4930) Co-authored-by: Iwan Kawrakow --- examples/quantize/quantize.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'examples/quantize') diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index f4e2175f..2ae04693 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -82,7 +82,7 @@ static void usage(const char * executable) { 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"); printf(" --pure: Disable k-quant mixtures and quantize all tensors to the same type\n"); - printf(" --imatrixfile_name: use data in file_name as importance matrix for quant optimizations\n"); + printf(" --imatrix file_name: use data in file_name as importance matrix for quant optimizations\n"); printf(" --include-weights tensor_name: use importance matrix for this/these tensor(s)\n"); printf(" --exclude-weights tensor_name: use importance matrix for this/these tensor(s)\n"); printf("Note: --include-weights and --exclude-weights cannot be used together\n"); -- cgit v1.2.3