diff --git a/tools/quantize/quantize.cpp b/tools/quantize/quantize.cpp index 7c9a7f29cc..59bf9bd3fd 100644 --- a/tools/quantize/quantize.cpp +++ b/tools/quantize/quantize.cpp @@ -686,11 +686,12 @@ 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 || - params.ftype == LLAMA_FTYPE_MOSTLY_IQ1_M) && imatrix_data.empty()) { + if (!params.dry_run && + ( + 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 || 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");