import os import json import argparse from datasets import Dataset from dotenv import load_dotenv load_dotenv() DATASET_NAME = "bkhmsi/test-realign-hackathon-red-team" TOKEN_ENV = "HF_TOKEN" def push_to_hf(token: str, stimuli: list[dict[str, str]]) -> None: dataset = Dataset.from_list(stimuli) print(f"> Pushing {len(dataset)} records to HF dataset {DATASET_NAME}") dataset.push_to_hub(DATASET_NAME, token=token, private=True) def read_jsonl(path: str) -> list[str]: with open(path, "r") as f: data = [json.loads(line) for line in f] return data def main() -> None: parser = argparse.ArgumentParser() parser.add_argument("--path", type=str, required=False, default="test_submissions/red_submission.jsonl", help="Path to the JSON file containing stimuli names.") args = parser.parse_args() path = args.path token = os.environ.get(TOKEN_ENV, "").strip() if not token: raise ValueError("Set HF_TOKEN before running this script.") stimuli = read_jsonl(path) push_to_hf(token, stimuli) if __name__ == "__main__": main()