Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-08-26 23:20:49 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '584d674be622fbf1578694ada6e62eebedbfd377' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/nix-flake-update.yml
#	Makefile
#	Package.swift
#	ggml-cuda.cu
#	tests/test-quantize-fns.cpp
This commit is contained in:
Concedo
2024-01-14 16:29:44 +08:00
parent bd77a48037 584d674be6
commit dc7bc0cb50
31 changed files with 2138 additions and 386 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/quantize/quantize.cpp
+1
View File
@@ -19,6 +19,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "Q5_0", LLAMA_FTYPE_MOSTLY_Q5_0, " 4.33G, +0.0683 ppl @ LLaMA-v1-7B", },
{ "Q5_1", LLAMA_FTYPE_MOSTLY_Q5_1, " 4.70G, +0.0349 ppl @ LLaMA-v1-7B", },
{ "Q2_K", LLAMA_FTYPE_MOSTLY_Q2_K, " 2.63G, +0.6717 ppl @ LLaMA-v1-7B", },
{ "Q2_K_S", LLAMA_FTYPE_MOSTLY_Q2_K_S, " 2.16G, +9.0634 ppl @ LLaMA-v1-7B", },
{ "Q3_K", LLAMA_FTYPE_MOSTLY_Q3_K_M, "alias for Q3_K_M" },
{ "Q3_K_S", LLAMA_FTYPE_MOSTLY_Q3_K_S, " 2.75G, +0.5551 ppl @ LLaMA-v1-7B", },
{ "Q3_K_M", LLAMA_FTYPE_MOSTLY_Q3_K_M, " 3.07G, +0.2496 ppl @ LLaMA-v1-7B", },