diff options
Diffstat (limited to 'examples')
| -rw-r--r-- | examples/quantize-stats/quantize-stats.cpp | 2 | ||||
| -rw-r--r-- | examples/quantize/quantize.cpp | 1 |
2 files changed, 3 insertions, 0 deletions
diff --git a/examples/quantize-stats/quantize-stats.cpp b/examples/quantize-stats/quantize-stats.cpp index 77302416..6d5f213d 100644 --- a/examples/quantize-stats/quantize-stats.cpp +++ b/examples/quantize-stats/quantize-stats.cpp @@ -378,6 +378,8 @@ int main(int argc, char ** argv) { printf("testing %s ...\n", ggml_type_name(type)); } + ggml_quantize_init(type); + error_stats global_stats {}; for (const auto& kv_tensor : tensors) { diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index 0236f218..a9673f0d 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -25,6 +25,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = { { "IQ2_XS", LLAMA_FTYPE_MOSTLY_IQ2_XS, " 2.31 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", }, { "Q3_K", LLAMA_FTYPE_MOSTLY_Q3_K_M, "alias for Q3_K_M" }, { "Q3_K_XS",LLAMA_FTYPE_MOSTLY_Q3_K_XS,"3-bit extra small quantization" , }, { "Q3_K_S", LLAMA_FTYPE_MOSTLY_Q3_K_S, " 2.75G, +0.5551 ppl @ LLaMA-v1-7B", }, |