diff options
Diffstat (limited to 'examples')
| -rw-r--r-- | examples/llama-bench/llama-bench.cpp | 3 | ||||
| -rw-r--r-- | examples/quantize/quantize.cpp | 1 |
2 files changed, 4 insertions, 0 deletions
diff --git a/examples/llama-bench/llama-bench.cpp b/examples/llama-bench/llama-bench.cpp index fc77be50..9e4fd266 100644 --- a/examples/llama-bench/llama-bench.cpp +++ b/examples/llama-bench/llama-bench.cpp @@ -327,6 +327,9 @@ static ggml_type ggml_type_from_name(const std::string & s) { if (s == "iq4_nl") { return GGML_TYPE_IQ4_NL; } + if (s == "q6_0") { + return GGML_TYPE_Q6_0; + } return GGML_TYPE_COUNT; } diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index c11b8631..2b240299 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -20,6 +20,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = { { "Q4_1", LLAMA_FTYPE_MOSTLY_Q4_1, " 3.90G, +0.1585 ppl @ LLaMA-v1-7B", }, { "Q5_0", LLAMA_FTYPE_MOSTLY_Q5_0, " 4.33G, +0.0683 ppl @ LLaMA-v1-7B", }, { "Q5_1", LLAMA_FTYPE_MOSTLY_Q5_1, " 4.70G, +0.0349 ppl @ LLaMA-v1-7B", }, + { "Q6_0", LLAMA_FTYPE_MOSTLY_Q6_0, " 6.5 bpw quantization", }, { "IQ2_XXS", LLAMA_FTYPE_MOSTLY_IQ2_XXS, " 2.06 bpw quantization", }, { "IQ2_XS", LLAMA_FTYPE_MOSTLY_IQ2_XS, " 2.31 bpw quantization", }, { "IQ2_S", LLAMA_FTYPE_MOSTLY_IQ2_S, " 2.5 bpw quantization", }, |