From 5d341757bc73efee0deba07a17679a965037753b Mon Sep 17 00:00:00 2001 From: Iwan Kawrakow Date: Mon, 29 Jul 2024 12:38:46 +0300 Subject: iq5_k: Basics Quantize/dequantize, CUDA dequantize --- examples/quantize/quantize.cpp | 1 + 1 file changed, 1 insertion(+) (limited to 'examples/quantize/quantize.cpp') diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index 5f599c65..17e87e53 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -42,6 +42,7 @@ static const std::vector QUANT_OPTIONS = { { "IQ4_XS", LLAMA_FTYPE_MOSTLY_IQ4_XS, " 4.25 bpw non-linear quantization", }, { "IQ2_K", LLAMA_FTYPE_MOSTLY_IQ2_K, " 2.375 bpw non-linear quantization",}, { "IQ4_K", LLAMA_FTYPE_MOSTLY_IQ4_K, " 4.5 bpw non-linear quantization", }, + { "IQ5_K", LLAMA_FTYPE_MOSTLY_IQ5_K, " 5.5 bpw non-linear quantization", }, { "Q4_K", LLAMA_FTYPE_MOSTLY_Q4_K_M, "alias for Q4_K_M", }, { "Q4_K_S", LLAMA_FTYPE_MOSTLY_Q4_K_S, " 3.59G, +0.0992 ppl @ LLaMA-v1-7B", }, { "Q4_K_M", LLAMA_FTYPE_MOSTLY_Q4_K_M, " 3.80G, +0.0532 ppl @ LLaMA-v1-7B", }, -- cgit v1.2.3