diff options
| author | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-06-16 15:56:32 +0300 |
|---|---|---|
| committer | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-06-22 12:02:51 +0300 |
| commit | 0f53bc30bbd4949be80562448419b4bbccd9490a (patch) | |
| tree | caadf89e3776d78b02f7d560e6d961305c4f14df /examples | |
| parent | f20b28558bdd20454ce891d36db5f37de819025a (diff) | |
bitnet: CUDA, scalar, AVX2
Diffstat (limited to 'examples')
| -rw-r--r-- | examples/quantize/quantize.cpp | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index 28584e14..06927890 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -26,6 +26,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = { { "IQ2_M", LLAMA_FTYPE_MOSTLY_IQ2_M, " 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, " 1.75 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", }, |