We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 8ad71f4 commit e2e2d77Copy full SHA for e2e2d77
examples/quantize/quantize.cpp
@@ -25,6 +25,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
25
{ "IQ2_S", LLAMA_FTYPE_MOSTLY_IQ2_S, " 2.5 bpw quantization", },
26
{ "IQ2_M", LLAMA_FTYPE_MOSTLY_IQ2_M, " 2.7 bpw quantization", },
27
{ "IQ2_XL", LLAMA_FTYPE_MOSTLY_IQ2_XL, " 2.85 bpw quantization mix", },
28
+ { "IQ1_XS", LLAMA_FTYPE_MOSTLY_IQ1_XS, " 1.6-1.7 bpw quantization mix", },
29
{ "IQ1_S", LLAMA_FTYPE_MOSTLY_IQ1_S, " 1.56 bpw quantization", },
30
{ "IQ1_M", LLAMA_FTYPE_MOSTLY_IQ1_M, " 1.75 bpw quantization", },
31
{ "Q2_K", LLAMA_FTYPE_MOSTLY_Q2_K, " 2.96G, +3.5199 ppl @ Llama-3-8B", },
0 commit comments