ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-25 07:34:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Report actual bpw

Browse Source
This commit is contained in:
Iwan Kawrakow
2024-11-15 17:05:18 +02:00
parent 3ee5434601
commit 5705dc7f2e
2 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/quantize/quantize.cpp
View File

@@ -32,8 +32,8 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "Q2_K", LLAMA_FTYPE_MOSTLY_Q2_K, " 2.63G, +0.6717 ppl @ LLaMA-v1-7B", },
{ "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 quantization", },
{ "IQ4_KT", LLAMA_FTYPE_MOSTLY_IQ4_KT, " 4.125 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_S", LLAMA_FTYPE_MOSTLY_IQ3_S, " 3.44 bpw quantization", },
{ "IQ3_M", LLAMA_FTYPE_MOSTLY_IQ3_M, " 3.66 bpw quantization mix", },
{ "Q3_K", LLAMA_FTYPE_MOSTLY_Q3_K_M, "alias for Q3_K_M" },
@@ -47,7 +47,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "IQ4_KSS", LLAMA_FTYPE_MOSTLY_IQ4_KSS, " 4.0 bpw non-linear quantization", },
{ "IQ2_K", LLAMA_FTYPE_MOSTLY_IQ2_K, " 2.375 bpw non-linear quantization",},
{ "IQ2_KS", LLAMA_FTYPE_MOSTLY_IQ2_KS, " 2.1875 bpw non-linear quantization",},
{ "IQ2_KT", LLAMA_FTYPE_MOSTLY_IQ2_KT, " 2.0625 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_KL", LLAMA_FTYPE_MOSTLY_IQ3_KL, " 4 bpw non-linear quantization mix",},
{ "IQ4_K", LLAMA_FTYPE_MOSTLY_IQ4_K, " 4.5 bpw non-linear quantization", },