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

format code

Browse source
This commit is contained in:
Trần Đức Nam 2023-12-19 15:01:42 +07:00
parent 1b300cbd58
commit 8fece75e35
2 changed files with 1 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

1
convert-hf-to-gguf.py
View file

@ -1006,7 +1006,6 @@ if args.awq_path:
else:
tmp_model_path.mkdir(parents=True, exist_ok=True)
print("Saving new weighted model ...")
tmp_model_path.mkdirs(exist_ok=True)
add_scale_weights(str(args.model), str(args.awq_path), str(tmp_model_path))
print(f"Saved weighted model at {tmp_model_path}.")
dir_model = tmp_model_path

3
convert.py
View file

@ -1139,7 +1139,7 @@ def main(args_in: list[str] | None = None) -> None:
# We currently only support Q8_0 output on little endian systems.
output_choices.append("q8_0")
parser = argparse.ArgumentParser(description="Convert a LLaMa model to a GGML compatible file")
parser.add_argument("--awq-path", type=Path, default=None, help="Path to scale awq cache file")
parser.add_argument("--awq-path", type=Path, help="Path to scale awq cache file", default=None)
parser.add_argument("--dump", action="store_true", help="don't convert, just show what's in the model")
parser.add_argument("--dump-single", action="store_true", help="don't convert, just show what's in a single model file")
parser.add_argument("--vocab-only", action="store_true", help="extract only the vocab")
@ -1161,7 +1161,6 @@ def main(args_in: list[str] | None = None) -> None:
else:
tmp_model_path.mkdir(parents=True, exist_ok=True)
print("Saving new weighted model ...")
tmp_model_path.mkdirs(exist_ok=True)
add_scale_weights(str(args.model), str(args.awq_path), str(tmp_model_path))
print(f"Saved weighted model at {tmp_model_path}.")
args.model = tmp_model_path