ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-06 20:10:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

iq2_s_r4: Zen4

Browse Source
This commit is contained in:
Iwan Kawrakow
2024-12-21 11:10:13 +02:00
parent a867b919ca
commit 964c5f9e82
10 changed files with 286 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View File

@@ -27,6 +27,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "IQ2_XS_R4",LLAMA_FTYPE_MOSTLY_IQ2_XS_R4,"IQ2_XS repacked", },
{ "IQ2_S", LLAMA_FTYPE_MOSTLY_IQ2_S, " 2.5 bpw quantization", },
{ "IQ2_M", LLAMA_FTYPE_MOSTLY_IQ2_M, " 2.7 bpw quantization", },
{ "IQ2_M_R4", LLAMA_FTYPE_MOSTLY_IQ2_M_R4, " 2.7 bpw quantization", },
{ "IQ1_S", LLAMA_FTYPE_MOSTLY_IQ1_S, " 1.56 bpw quantization", },
{ "IQ1_M", LLAMA_FTYPE_MOSTLY_IQ1_M, " 1.75 bpw quantization", },
{ "IQ1_BN", LLAMA_FTYPE_MOSTLY_IQ1_BN, " 1.62 bpw quantization (Bitnet)", },