From 93419de68f90fede135480a2717785d519df9f42 Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Sat, 21 Dec 2024 11:26:35 +0100 Subject: IQ2_S_R4 (#156) * iq2_s_r4: Zen4 * Minor * iq2_s_r4: NEON --------- Co-authored-by: Iwan Kawrakow --- examples/quantize/quantize.cpp | 1 + 1 file changed, 1 insertion(+) (limited to 'examples') diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index dbae9792..1599405b 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -27,6 +27,7 @@ static const std::vector QUANT_OPTIONS = { { "IQ2_XS_R4",LLAMA_FTYPE_MOSTLY_IQ2_XS_R4,"IQ2_XS repacked", }, { "IQ2_S", LLAMA_FTYPE_MOSTLY_IQ2_S, " 2.5 bpw quantization", }, { "IQ2_M", LLAMA_FTYPE_MOSTLY_IQ2_M, " 2.7 bpw quantization", }, + { "IQ2_M_R4", LLAMA_FTYPE_MOSTLY_IQ2_M_R4, " 2.7 bpw quantization", }, { "IQ1_S", LLAMA_FTYPE_MOSTLY_IQ1_S, " 1.56 bpw quantization", }, { "IQ1_M", LLAMA_FTYPE_MOSTLY_IQ1_M, " 1.75 bpw quantization", }, { "IQ1_BN", LLAMA_FTYPE_MOSTLY_IQ1_BN, " 1.62 bpw quantization (Bitnet)", }, -- cgit v1.2.3