mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
6097186a95
* Add Datasets: MedQA, ProteinLMBench; Add Models: huatuogpt, baichuanM1 * Fix bugs for MedQA. Add info in dataset-index * Add version code for MedQA and ProteinLMBench * Add version code for MedQA and ProteinLMBench
30 lines
735 B
Python
30 lines
735 B
Python
from datasets import Dataset, load_dataset
|
|
|
|
from opencompass.registry import LOAD_DATASET
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class MedQADataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load_single(path):
|
|
dataset = []
|
|
ds = load_dataset(path)
|
|
for data in ds['train']:
|
|
data['label'] = data['answer_idx']
|
|
choices = ''
|
|
for option in data['options']:
|
|
choices += option + '. ' + data['options'][option] + '\n'
|
|
data['choices'] = choices
|
|
|
|
dataset.append(data)
|
|
|
|
return Dataset.from_list(dataset)
|
|
|
|
@staticmethod
|
|
def load(path):
|
|
dataset = MedQADataset.load_single(path)
|
|
return dataset
|