8000 fix quantize example by iyubondyrev · Pull Request #1387 · abetlen/llama-cpp-python · GitHub
[go: up one dir, main page]
Skip to content

fix quantize example #1387

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 28, 2024
Merged

fix quantize example #1387

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 8 additions & 5 deletions examples/low_level_api/quantize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,14 +4,16 @@


def main(args):
fname_inp = args.fname_inp.encode("utf-8")
fname_out = args.fname_out.encode("utf-8")
if not os.path.exists(fname_inp):
raise RuntimeError(f"Input file does not exist ({fname_inp})")
if os.path.exists(fname_out):
raise RuntimeError(f"Output file already exists ({fname_out})")
fname_inp = args.fname_inp.encode("utf-8")
fname_out = args.fname_out.encode("utf-8")
itype = args.itype
return_code = llama_cpp.llama_model_quantize(fname_inp, fname_out, itype)
ftype = args.type
args = llama_cpp.llama_model_quantize_default_params()
args.ftype = ftype
return_code = llama_cpp.llama_model_quantize(fname_inp, fname_out, args)
if return_code != 0:
raise RuntimeError("Failed to quantize model")

Expand All @@ -20,6 +22,7 @@ def main(args):
parser = argparse.ArgumentParser()
parser.add_argument("fname_inp", type=str, help="Path to input model")
parser.add_argument("fname_out", type=str, help="Path to output model")
parser.add_argument("type", type=int, help="Type of quantization (2: q4_0, 3: q4_1)")
parser.add_argument("type", type=int, help="Type of quantization (2: q4_0, 3: q4_1), see llama_cpp.py for enum")
args = parser.parse_args()
main(args)

0