From f6863cfa1bbc5ac42b78837b355e45d82246a472 Mon Sep 17 00:00:00 2001 From: Iwan Kawrakow Date: Mon, 17 Jun 2024 18:41:30 +0300 Subject: bitnet: add 2 bpw quantization The scalar dot product already chieves 37 t/s for TG! --- 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 06927890..a5ffb2b2 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -27,6 +27,7 @@ static const std::vector QUANT_OPTIONS = { { "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, " 1.75 bpw quantization (Bitnet)", }, + { "IQ2_BN", LLAMA_FTYPE_MOSTLY_IQ2_BN, " 2.00 bpw quantization (Bitnet)", }, { "Q2_K", LLAMA_FTYPE_MOSTLY_Q2_K, " 2.63G, +0.6717 ppl @ LLaMA-v1-7B", }, { "Q2_K_S", LLAMA_FTYPE_MOSTLY_Q2_K_S, " 2.16G, +9.0634 ppl @ LLaMA-v1-7B", }, { "IQ3_XXS",LLAMA_FTYPE_MOSTLY_IQ3_XXS," 3.06 bpw quantization", }, -- cgit v1.2.3