datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
humaneval_infilling
HumanEval-Infilling
Dataset Summary
HumanEval-Infilling is a benchmark for infilling tasks, derived from HumanEval benchmark for the evaluation of code generation models.
Dataset Structure
To load the dataset you need to specify a subset. By default HumanEval-SingleLineInfilling is loaded.
from datasets import load_dataset
ds = load_dataset("humaneval_infilling", "HumanEval-RandomSpanInfilling")
DatasetDict({
test: Dataset({
features: ['task_id'… See the full description on the dataset page: https://huggingface.co/datasets/Sculpt-AI/humaneval_infilling.sculpt-eval-dataset