diff options
Diffstat (limited to 'examples/quantize/quantize.cpp')
| -rw-r--r-- | examples/quantize/quantize.cpp | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index b5277ec1..85ceabfd 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -46,6 +46,8 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = { { "Q2_K_R4", LLAMA_FTYPE_MOSTLY_Q2_K_R4, "Q2_K_S repacked", }, { "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", }, + { "IQ3_KT", LLAMA_FTYPE_MOSTLY_IQ3_KT, " 3.125 bpw trellis quantization", }, + { "IQ4_KT", LLAMA_FTYPE_MOSTLY_IQ4_KT, " 4.0 bpw trellis quantization", }, { "IQ3_XXS_R4",LLAMA_FTYPE_MOSTLY_IQ3_XXS_R4,"IQ3_XXS repacked", }, { "IQ3_S", LLAMA_FTYPE_MOSTLY_IQ3_S, " 3.44 bpw quantization", }, { "IQ3_S_R4", LLAMA_FTYPE_MOSTLY_IQ3_S_R4, "IQ3_S repacked", }, @@ -73,6 +75,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = { { "IQ2_K", LLAMA_FTYPE_MOSTLY_IQ2_K, " 2.375 bpw non-linear quantization",}, { "IQ2_K_R4", LLAMA_FTYPE_MOSTLY_IQ2_K_R4, "IQ2_K repacked",}, { "IQ2_KS", LLAMA_FTYPE_MOSTLY_IQ2_KS, " 2.1875 bpw non-linear quantization",}, + { "IQ2_KT", LLAMA_FTYPE_MOSTLY_IQ2_KT, " 2.125 bpw trellis quantization", }, { "IQ3_K", LLAMA_FTYPE_MOSTLY_IQ3_K, " 3.44 bpw non-linear quantization", }, { "IQ3_K_R4", LLAMA_FTYPE_MOSTLY_IQ3_K_R4, "IQ3_K repacked", }, { "IQ3_KL", LLAMA_FTYPE_MOSTLY_IQ3_KL, " 4 bpw non-linear quantization mix",}, |