Skip to content

Exposing keyword arguments for LAB-Bench dataset loading #336

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jamesbraza merged 2 commits into from
Feb 2, 2026
Merged

Exposing keyword arguments for LAB-Bench dataset loading #336

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4f87959
Exposed dataset loading keyword arguments for LAB-Bench
jamesbraza Jan 30, 2026
ea4a63c
Using kwargs to load_dataset to avoid name collisions
jamesbraza Jan 30, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion packages/labbench/src/aviary/envs/labbench/task.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -263,6 +263,7 @@ def read_ds_from_hub(
hf_split: str,
randomize: bool = True,
seed: int | None = None,
**load_ds_kwargs,
) -> "pd.DataFrame":
"""
Read in a train or test DataFrame.
Expand All @@ -274,6 +275,7 @@ def read_ds_from_hub(
hf_split: Hugging Face Hub dataset's split, e.g. "train" or "test".
randomize: Opt-out flag to shuffle the dataset after loading in by question.
seed: Random seed to use for the shuffling.
load_ds_kwargs: Keyword arguments to pass to the internal load_dataset call.

Raises:
DatasetNotFoundError: If any of the datasets are not found, or the
Expand All @@ -289,7 +291,9 @@ def read_ds_from_hub(

if isinstance(hf_name, LABBenchDatasets):
hf_name = hf_name.value
ds = load_dataset(hf_path, hf_name, split=hf_split).to_pandas()
ds = load_dataset(
**(load_ds_kwargs | {"path": hf_path, "name": hf_name, "split": hf_split})
).to_pandas()
if "distractors" in ds.columns:
# Convert to list so it's not unexpectedly a numpy array
ds["distractors"] = ds["distractors"].apply(list)
Expand Down