def parse_eval_args()

in evaluation.py [0:0]


def parse_eval_args() -> argparse.Namespace:
    parser = argparse.ArgumentParser(formatter_class=argparse.RawTextHelpFormatter)
    parser.add_argument("--config", default="", help="Path to a yaml file specifying all eval arguments, will ignore cli arguments if specified")
    parser.add_argument("--model", default="hf", help="Name of model e.g. `hf`")
    parser.add_argument(
        "--tasks",
        default=None,
        help="To get full list of tasks, use the command lmms-eval --tasks list",
    )
    parser.add_argument(
        "--model_args",
        default="",
        help="String arguments for model, e.g. `pretrained=EleutherAI/pythia-160m,dtype=float32`",
    )
    parser.add_argument(
        "--num_fewshot",
        type=int,
        default=None,
        help="Number of examples in few-shot context",
    )
    parser.add_argument(
        "--batch_size",
        "-b",
        type=str,
        default=128,
        metavar="auto|auto:N|N",
        help="Acceptable values are 'auto', 'auto:N' or N, where N is an integer. Default 1.",
    )
    parser.add_argument(
        "--max_batch_size",
        type=int,
        default=None,
        metavar="N",
        help="Maximal batch size to try with --batch_size auto.",
    )
    parser.add_argument(
        "--device",
        type=str,
        default='cuda',
        help="Device to use (e.g. cuda, cuda:0, cpu)",
    )
    parser.add_argument(
        "--output_path",
        default='results/',
        type=str,
        metavar="= [dir/file.jsonl] [DIR]",
        help="The path to the output file where the result metrics will be saved. If the path is a directory and log_samples is true, the results will be saved in the directory. Else the parent directory will be used.",
    )
    parser.add_argument(
        "--limit",
        type=float,
        default=None,
        help="Limit the number of examples per task. " "If <1, limit is a percentage of the total number of examples.",
    )
    parser.add_argument(
        "--use_cache",
        "-c",
        type=str,
        default=None,
        metavar="DIR",
        help="A path to a sqlite db file for caching model responses. `None` if not caching.",
    )
    parser.add_argument(
        "--cache_requests",
        type=str,
        default=None,
        choices=["true", "refresh", "delete"],
        help="Speed up evaluation by caching the building of dataset requests. `None` if not caching.",
    )
    parser.add_argument(
        "--check_integrity",
        action="store_true",
        help="Whether to run the relevant part of the test suite for the tasks",
    )
    parser.add_argument(
        "--write_out",
        "-w",
        action="store_true",
        default=False,
        help="Prints the prompt for the first few documents.",
    )
    parser.add_argument(
        "--log_samples",
        action="store_true",
        default=False,
        help="If True, write out all model outputs and documents for per-sample measurement and post-hoc analysis",
    )
    parser.add_argument(
        "--wandb_log_samples",
        action="store_true",
        default=False,
        help="If True, write out all model outputs and documents for per-sample measurement and post-hoc analysis to Weights and Biases",
    )
    parser.add_argument(
        "--log_samples_suffix",
        type=str,
        default="model_outputs",
        help="Specify a suffix for the log_samples file name.",
    )
    parser.add_argument(
        "--system_instruction",
        type=str,
        default=None,
        help="System instruction to be used in the prompt",
    )
    parser.add_argument(
        "--apply_chat_template",
        action="store_true",
        default=False,
        help="If True, applies the chat template to the prompt",
    )
    parser.add_argument(
        "--fewshot_as_multiturn",
        action="store_true",
        default=False,
        help="If True, uses the fewshot as a multi-turn conversation",
    )
    parser.add_argument(
        "--show_config",
        action="store_true",
        default=False,
        help="If True, shows the the full config of all tasks at the end of the evaluation.",
    )
    parser.add_argument(
        "--include_path",
        type=str,
        default=None,
        help="Additional path to include if there are external tasks to include.",
    )
    parser.add_argument(
        "--gen_kwargs",
        default="",
        help=("String arguments for model generation on greedy_until tasks," " e.g. `temperature=0,top_k=0,top_p=0`"),
    )
    parser.add_argument(
        "--verbosity",
        type=str,
        default="INFO",
        help="Log error when tasks are not registered.",
    )
    parser.add_argument(
        "--wandb_args",
        default="",
        help="Comma separated string arguments passed to wandb.init, e.g. `project=lmms-eval,job_type=eval",
    )
    parser.add_argument(
        "--timezone",
        default="Asia/Singapore",
        help="Timezone for datetime string, e.g. Asia/Singapore, America/New_York, America/Los_Angeles. You can check the full list via `import pytz; print(pytz.common_timezones)`",
    )
    parser.add_argument(
        "--hf_hub_log_args",
        type=str,
        default="",
        help="Comma separated string arguments passed to Hugging Face Hub's log function, e.g. `hub_results_org=EleutherAI,hub_repo_name=lm-eval-results`",
    )
    parser.add_argument(
        "--predict_only",
        "-x",
        action="store_true",
        default=False,
        help="Use with --log_samples. Only model outputs will be saved and metrics will not be evaluated.",
    )
    default_seed_string = '0'
    parser.add_argument(
        "--seed",
        type=partial(_int_or_none_list_arg_type, 3, 4, default_seed_string),
        default=default_seed_string,  # for backward compatibility
        help=(
            "Set seed for python's random, numpy, torch, and fewshot sampling.\n"
            "Accepts a comma-separated list of 4 values for python's random, numpy, torch, and fewshot sampling seeds, "
            "respectively, or a single integer to set the same seed for all four.\n"
            f"The values are either an integer or 'None' to not set the seed. Default is `{default_seed_string}` "
            "(for backward compatibility).\n"
            "E.g. `--seed 0,None,8,52` sets `random.seed(0)`, `torch.manual_seed(8)`, and fewshot sampling seed to 52. "
            "Here numpy's seed is not set since the second value is `None`.\n"
            "E.g, `--seed 42` sets all four seeds to 42."
        ),
    )
    parser.add_argument(
        "--trust_remote_code",
        action="store_true",
        help="Sets trust_remote_code to True to execute code to create HF Datasets from the Hub",
    )
    parser.add_argument("--process_with_media", action="store_true", help="Whether you will process you dataset with audio, image. By default set to False" "In case some benchmarks need to be processed with media, set this flag to True.")
    args = parser.parse_args()
    return args