diff options
Diffstat (limited to 'examples')
| -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 a8b4a44e..f8ce3edd 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -41,6 +41,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = { { "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_R4",LLAMA_FTYPE_MOSTLY_IQ4_XS_R4," 4.25 bpw non-linear quantization", }, { "Q4_0_R4", LLAMA_FTYPE_MOSTLY_Q4_0_R4, " 4.50 bpw quantization", }, { "Q5_0_R4", LLAMA_FTYPE_MOSTLY_Q5_0_R4, " 5.50 bpw quantization", }, { "Q6_0_R4", LLAMA_FTYPE_MOSTLY_Q6_0_R4, " 6.50 bpw quantization", }, |