ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-01 20:19:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

iq5_k: Basics

Browse Source 
Quantize/dequantize, CUDA dequantize
This commit is contained in:
Iwan Kawrakow
2024-07-29 12:38:46 +03:00
committed by Kawrakow
parent 06e255ac9d
commit 5d341757bc
14 changed files with 650 additions and 178 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View File

@@ -42,6 +42,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "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",},
{ "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", },
{ "Q4_K_S", LLAMA_FTYPE_MOSTLY_Q4_K_S, " 3.59G, +0.0992 ppl @ LLaMA-v1-7B", },
{ "Q4_K_M", LLAMA_FTYPE_MOSTLY_Q4_K_M, " 3.80G, +0.0532 ppl @ LLaMA-v1-7B", },