ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-01-31 03:29:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

iq3_k: Basics

Browse Source 
Quantize/dequantize, CUDA dequantize.
PPL of LLaMA-3.1-8B is better than iq3_s and iq3_m.
This commit is contained in:
Iwan Kawrakow
2024-07-30 16:11:25 +03:00
committed by Kawrakow
parent 36204c4ec7
commit 4f237d44f6
15 changed files with 416 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View File

@@ -41,6 +41,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "IQ4_NL", LLAMA_FTYPE_MOSTLY_IQ4_NL, " 4.50 bpw non-linear quantization", },
{ "IQ4_XS", LLAMA_FTYPE_MOSTLY_IQ4_XS, " 4.25 bpw non-linear quantization", },
{ "IQ2_K", LLAMA_FTYPE_MOSTLY_IQ2_K, " 2.375 bpw non-linear quantization",},
{ "IQ3_K", LLAMA_FTYPE_MOSTLY_IQ3_K, " 3.44 bpw non-linear quantization", },
{ "IQ4_K", LLAMA_FTYPE_MOSTLY_IQ4_K, " 4.5 bpw non-linear quantization", },
{ "IQ5_K", LLAMA_FTYPE_MOSTLY_IQ5_K, " 5.5 bpw non-linear quantization", },
{ "Q4_K", LLAMA_FTYPE_MOSTLY_Q4_K_M, "alias for Q4_K_M", },