vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

convert_lora_to_gguf.py: remove model_name parameter. Doesn't exist in LoraModel()

Browse source
This commit is contained in:
brian khuu 2024-07-17 01:11:27 +10:00
parent eb0bf6b92f
commit 7e9271cabf
1 changed files with 1 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

3
convert_lora_to_gguf.py
View file

@ -356,8 +356,7 @@ if __name__ == '__main__':
fname_out,
is_big_endian=args.bigendian,
use_temp_file=False,
eager=args.no_lazy,
model_name=None,
eager=args.no_lazy
)
with open(lora_config, "r") as f: