vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Optimizations

Browse source
This commit is contained in:
Concedo 2023-03-24 21:33:53 +08:00
parent 3879d84400
commit c6c60332a4
3 changed files with 10 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_for_kobold.py
View file

@ -289,7 +289,7 @@ if __name__ == '__main__':
mdl_nparts += 1
modelname = os.path.abspath(sys.argv[1])
print("Loading model: " + modelname)
loadok = load_model(modelname,16,maxctx,mdl_nparts)
loadok = load_model(modelname,8,maxctx,mdl_nparts)
print("Load Model OK: " + str(loadok))
#friendlymodelname = Path(modelname).stem ### this wont work on local kobold api, so we must hardcode a known HF model name