From 167479e0272dcb5f9babc7668664fa2a75c4f2dd Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Mon, 23 Dec 2024 14:34:23 +0100 Subject: IQ3_S_R4 (#162) * iq3_s_r4: WIP * iq3_s_r4: Zen4 * iq3_s_r4: slightly better Zen4 * iq3_s_r4: AVX2 * iq3_s_r4: NEON * iq3_s_r4: rearrange quants * iq3_s_r4: rearranged quants - AVX2 * iq3_s_r4: rearranged quants - NEON --------- Co-authored-by: Iwan Kawrakow --- examples/quantize/quantize.cpp | 1 + 1 file changed, 1 insertion(+) (limited to 'examples/quantize') diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index 1599405b..5ffdbc84 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -39,6 +39,7 @@ static const std::vector QUANT_OPTIONS = { { "IQ3_XXS", LLAMA_FTYPE_MOSTLY_IQ3_XXS, " 3.06 bpw quantization", }, { "IQ3_XXS_R4",LLAMA_FTYPE_MOSTLY_IQ3_XXS_R4,"IQ3_XXS repacked", }, { "IQ3_S", LLAMA_FTYPE_MOSTLY_IQ3_S, " 3.44 bpw quantization", }, + { "IQ3_S_R4", LLAMA_FTYPE_MOSTLY_IQ3_S_R4, "IQ3_S repacked", }, { "IQ3_M", LLAMA_FTYPE_MOSTLY_IQ3_M, " 3.66 bpw quantization mix", }, { "Q3_K", LLAMA_FTYPE_MOSTLY_Q3_K_M, "alias for Q3_K_M" }, { "Q3_K_R4", LLAMA_FTYPE_MOSTLY_Q3_K_R4, "Q3_K_S repacked" }, -- cgit v1.2.3