diff options
Diffstat (limited to 'examples')
| -rw-r--r-- | examples/quantize/quantize.cpp | 11 |
1 files changed, 7 insertions, 4 deletions
diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index eed92c5a..80c493f1 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_S", LLAMA_FTYPE_MOSTLY_IQ2_S, " 2.5 bpw quantization", }, { "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", }, { "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", }, @@ -370,10 +371,12 @@ int main(int argc, char ** argv) { if ((params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_XS || params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_XXS || params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_S || - params.ftype == LLAMA_FTYPE_MOSTLY_Q2_K_S || params.ftype == LLAMA_FTYPE_MOSTLY_IQ1_S) && imatrix_data.empty()) { - fprintf(stderr, "\n===============================================================================================\n"); - fprintf(stderr, "Please do not use IQ1_S, IQ2_XXS, IQ2_XS or Q2_K_S quantization without an importance matrix\n"); - fprintf(stderr, "===============================================================================================\n\n\n"); + params.ftype == LLAMA_FTYPE_MOSTLY_Q2_K_S || + params.ftype == LLAMA_FTYPE_MOSTLY_IQ1_S || + params.ftype == LLAMA_FTYPE_MOSTLY_IQ1_M) && imatrix_data.empty()) { + fprintf(stderr, "\n==========================================================================================================\n"); + fprintf(stderr, "Please do not use IQ1_S, IQ1_M, IQ2_S, IQ2_XXS, IQ2_XS or Q2_K_S quantization without an importance matrix\n"); + fprintf(stderr, "==========================================================================================================\n\n\n"); return 1; } |