diff options
Diffstat (limited to 'examples/quantize/quantize.cpp')
| -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 b5907e2b..333fae36 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -40,6 +40,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = { { "Q3_K_M", LLAMA_FTYPE_MOSTLY_Q3_K_M, " 3.07G, +0.2496 ppl @ LLaMA-v1-7B", }, { "Q3_K_L", LLAMA_FTYPE_MOSTLY_Q3_K_L, " 3.35G, +0.1764 ppl @ LLaMA-v1-7B", }, { "IQ4_NL", LLAMA_FTYPE_MOSTLY_IQ4_NL, " 4.50 bpw non-linear quantization", }, + { "IQ4_NL_X4",LLAMA_FTYPE_MOSTLY_IQ4_NL_X4," 4.50 bpw non-linear quantization", }, { "IQ4_XS", LLAMA_FTYPE_MOSTLY_IQ4_XS, " 4.25 bpw non-linear quantization", }, { "IQ4_KS", LLAMA_FTYPE_MOSTLY_IQ4_KS, " 4.25 bpw non-linear quantization", }, { "IQ4_KSS", LLAMA_FTYPE_MOSTLY_IQ4_KSS, " 4.0 bpw non-linear quantization", }, |