vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge commit '947538acb8' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/docker.yml
#	CMakePresets.json
#	examples/llama-bench/llama-bench.cpp
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-quantize-fns.cpp
This commit is contained in:
Concedo 2024-09-09 11:26:34 +08:00
commit 70cdb55cc9
29 changed files with 93418 additions and 92397 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/quantize/quantize.cpp
View file

@ -27,6 +27,8 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "IQ2_M", LLAMA_FTYPE_MOSTLY_IQ2_M, " 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", },
{ "TQ1_0", LLAMA_FTYPE_MOSTLY_TQ1_0, " 1.69 bpw ternarization", },
{ "TQ2_0", LLAMA_FTYPE_MOSTLY_TQ2_0, " 2.06 bpw ternarization", },
{ "Q2_K", LLAMA_FTYPE_MOSTLY_Q2_K, " 2.96G, +3.5199 ppl @ Llama-3-8B", },
{ "Q2_K_S", LLAMA_FTYPE_MOSTLY_Q2_K_S, " 2.96G, +3.1836 ppl @ Llama-3-8B", },
{ "IQ3_XXS", LLAMA_FTYPE_MOSTLY_IQ3_XXS, " 3.06 bpw quantization", },