INNER CODE UNIT · Python
main
HIT-SCIR/Chinese-Mixtral-8x7B · data/parquet2jsonl.py:21
def main(
target_jsonl: str = "./data/en/DKYoon-SlimPajama-6B.jsonl",
root: str = "./data/en/DKYoon-SlimPajama-6B/data",
):
root = Path(root)
target_jsonl = Path(target_jsonl)
files = os.listdir(root)
with open(target_jsonl, "w") as f:
for file in tqdm(files):
objs = parse_file(root / file)
for obj_str in list(objs):
try:
obj = json.loads(obj_str)
f.write(f"{json.dumps(obj, ensure_ascii=False)}\n")
except:
print("json parse error")