From c55e66f99764eac5ff09ca8ff21c1342e7313ba5 Mon Sep 17 00:00:00 2001 From: Iwan Kawrakow Date: Fri, 8 Mar 2024 15:14:28 +0200 Subject: [PATCH] iq1s_blocks16: Use 2* as sigma2 in weight adjustment --- ggml-quants.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ggml-quants.c b/ggml-quants.c index 3bdb37ec8..cafd0129d 100644 --- a/ggml-quants.c +++ b/ggml-quants.c @@ -11606,7 +11606,7 @@ static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy const float * xbl = x + QK_K*ibl; float sumx2 = 0; for (int i = 0; i < QK_K; ++i) sumx2 += xbl[i]*xbl[i]; - float sigma2 = sumx2/QK_K; + float sigma2 = 2*sumx2/QK_K; for (int ib = 0; ib < QK_K/IQ1S_BLOCK_SIZE; ++ib) { const float * xb = xbl + IQ1S_BLOCK_SIZE*ib;