def create_parser()

in extract.py [0:0]

• 42 lines of code
• 1 McCabe index (conditional complexity)

def create_parser():
    parser = argparse.ArgumentParser(
        description="Extract per-token representations and model outputs for sequences in a FASTA file"  # noqa
    )

    parser.add_argument(
        "model_location",
        type=str,
        help="PyTorch model file OR name of pretrained model to download (see README for models)",
    )
    parser.add_argument(
        "fasta_file",
        type=pathlib.Path,
        help="FASTA file on which to extract representations",
    )
    parser.add_argument(
        "output_dir",
        type=pathlib.Path,
        help="output directory for extracted representations",
    )

    parser.add_argument("--toks_per_batch", type=int, default=4096, help="maximum batch size")
    parser.add_argument(
        "--repr_layers",
        type=int,
        default=[-1],
        nargs="+",
        help="layers indices from which to extract representations (0 to num_layers, inclusive)",
    )
    parser.add_argument(
        "--include",
        type=str,
        nargs="+",
        choices=["mean", "per_tok", "bos", "contacts"],
        help="specify which representations to return",
        required=True,
    )
    parser.add_argument(
        "--truncate",
        action="store_true",
        help="Truncate sequences longer than 1024 to match the training setup",
    )

    parser.add_argument("--nogpu", action="store_true", help="Do not use GPU even if available")
    return parser