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

Adding iq4_kt - not competitive at this point

Browse Source
This commit is contained in:
Iwan Kawrakow
2024-11-11 12:34:00 +02:00
parent 47b28c1e92
commit 00b4bff286
12 changed files with 343 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View File

@@ -33,6 +33,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "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_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" },