You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
 

16 lines
528 B

"""Lightweight dataset helpers (dummy datasets, episode attention masks)."""
from datasets import Dataset
def create_dummy_dataset(num_samples: int = 100) -> Dataset:
"""Create a dummy dataset with the specified number of samples.
Args:
num_samples (int): Number of samples to create in the dataset.
Returns:
Dataset: A HuggingFace Dataset containing dummy prompts.
"""
dummy_data = {"prompt": [f"Sample prompt {i}" for i in range(num_samples)]}
return Dataset.from_dict(dummy_data)