mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
b2da1c08a8
* [Dataset] Add SmolInstruct, Update Chembench * Add dataset metadata * update * update * update
37 lines
1.0 KiB
Python
37 lines
1.0 KiB
Python
import json
|
|
import os.path as osp
|
|
|
|
from datasets import Dataset, DatasetDict
|
|
|
|
from opencompass.registry import LOAD_DATASET
|
|
from opencompass.utils import get_data_path
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class ChemBenchDataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path: str, name: str):
|
|
dataset = DatasetDict()
|
|
path = get_data_path(path)
|
|
for split in ['dev', 'test']:
|
|
raw_data = []
|
|
filename = osp.join(path, split, f'{name}_benchmark.json')
|
|
with open(filename, 'r', encoding='utf-8') as json_file:
|
|
data = json.load(json_file)
|
|
|
|
for item in data:
|
|
raw_data.append({
|
|
'input': item['question'],
|
|
'A': item['A'],
|
|
'B': item['B'],
|
|
'C': item['C'],
|
|
'D': item['D'],
|
|
'target': item['answer'],
|
|
})
|
|
|
|
dataset[split] = Dataset.from_list(raw_data)
|
|
return dataset
|