OpenCompass/opencompass/datasets/longbench/longbench_vcsum.py
2024-08-15 11:30:30 +08:00

26 lines
836 B
Python

from datasets import Dataset, load_dataset
from opencompass.registry import LOAD_DATASET
from opencompass.utils import get_data_path
from ..base import BaseDataset
@LOAD_DATASET.register_module()
class LongBenchvcsumDataset(BaseDataset):
@staticmethod
def load(**kwargs):
if 'data_files' in kwargs:
kwargs['data_files'] = get_data_path(kwargs['data_files'],
local_mode=True)
dataset = load_dataset(**kwargs)
split = 'test'
raw_data = []
for i in range(len(dataset[split])):
context = dataset[split]['context'][i]
answers = dataset[split]['answers'][i]
raw_data.append({'context': context, 'answers': answers})
dataset[split] = Dataset.from_list(raw_data)
return dataset