ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-11 22:40:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Something is still wrong

Browse Source
This commit is contained in:
Iwan Kawrakow
2024-12-08 19:48:15 +02:00
parent 43e65a672a
commit 24d3bf2e70
10 changed files with 276 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View File

@@ -58,6 +58,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "IQ5_K", LLAMA_FTYPE_MOSTLY_IQ5_K, " 5.5 bpw non-linear quantization", },
{ "IQ6_K", LLAMA_FTYPE_MOSTLY_IQ6_K, " 6.6 bpw non-linear quantization", },
{ "Q4_K", LLAMA_FTYPE_MOSTLY_Q4_K_M, "alias for Q4_K_M", },
{ "Q4_K_R4", LLAMA_FTYPE_MOSTLY_Q4_K_R4, "Q4_K_S repacked", },
{ "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", },
{ "Q5_K", LLAMA_FTYPE_MOSTLY_Q5_K_M, "alias for Q5_K_M", },