diff options
Diffstat (limited to 'convert.py')
| -rwxr-xr-x | convert.py | 13 |
1 files changed, 0 insertions, 13 deletions
@@ -1377,7 +1377,6 @@ 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, 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") @@ -1393,18 +1392,6 @@ def main(args_in: list[str] | None = None) -> None: parser.add_argument("--skip-unknown", action="store_true", help="skip unknown tensor names instead of failing") args = parser.parse_args(args_in) - if args.awq_path: - sys.path.insert(1, str(Path(__file__).parent / 'awq-py')) - from awq.apply_awq import add_scale_weights # type: ignore[import-not-found] - tmp_model_path = args.model / "weighted_model" - if tmp_model_path.is_dir(): - print(f"{tmp_model_path} exists as a weighted model.") - else: - tmp_model_path.mkdir(parents=True, exist_ok=True) - print("Saving new weighted model ...") - 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 if args.dump_single: model_plus = lazy_load_file(args.model) |