From cfec4048abc478cd2769d1908e3ecc53ad2f28bd Mon Sep 17 00:00:00 2001 From: Ed Addario Date: Tue, 19 Aug 2025 10:43:51 +0100 Subject: [PATCH] Update usage --- tools/quantize/quantize.cpp | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/quantize/quantize.cpp b/tools/quantize/quantize.cpp index 470dc3d916..b2d62f1490 100644 --- a/tools/quantize/quantize.cpp +++ b/tools/quantize/quantize.cpp @@ -132,6 +132,7 @@ static void usage(const char * executable) { printf(" Advanced option to selectively quantize tensors. May be specified multiple times.\n"); printf(" --prune-layers L0,L1,L2...comma-separated list of layer numbers to prune from the model\n"); printf(" Advanced option to remove all tensors from the given layers\n"); + printf(" --target-bpw: target bits per weight (bpw). Must be a positive number between 0.0 and 8.0 \n"); printf(" --keep-split: will generate quantized model in the same shards as input\n"); printf(" --override-kv KEY=TYPE:VALUE\n"); printf(" Advanced option to override model metadata by key in the quantized model. May be specified multiple times.\n");