feat(dataset): accept token argument for private HF Hub datasets (#4136)

docs/source/using_dataset_tools.mdx

@@ -252,6 +252,10 @@ lerobot-dataset-viz \
     --episode-index 0
 ```
 
+For a private or gated dataset, authenticate first with `hf auth login`, or set the
+`HF_TOKEN` environment variable. The Hub client then discovers the credential
+automatically; no token argument is needed.
+
 **From a local folder:**
 Add the `--root` option and set `--mode local`. For example, to search in `./my_local_data_dir/lerobot/pusht`:
 

src/lerobot/datasets/dataset_metadata.py

@@ -73,6 +73,8 @@ class LeRobotDatasetMetadata:
         revision: str | None = None,
         force_cache_sync: bool = False,
         metadata_buffer_size: int = 10,
+        *,
+        token: str | bool | None = None,
     ):
         """Load or download metadata for an existing LeRobot dataset.
 
@@ -94,6 +96,10 @@ class LeRobotDatasetMetadata:
                 even when local files exist.
             metadata_buffer_size: Number of episode metadata records to buffer
                 in memory before flushing to parquet.
+            token: Authentication token used for Hub requests. Pass a string
+                token, ``True`` to require the locally stored token, ``False``
+                to disable authentication, or ``None`` to use the Hugging Face
+                Hub default.
         """
         self.repo_id = repo_id
         self.revision = revision if revision else CODEBASE_VERSION
@@ -113,9 +119,12 @@ class LeRobotDatasetMetadata:
             self._load_metadata()
         except (FileNotFoundError, NotADirectoryError):
             if is_valid_version(self.revision):
-                self.revision = get_safe_version(self.repo_id, self.revision)
+                if token is None:
+                    self.revision = get_safe_version(self.repo_id, self.revision)
+                else:
+                    self.revision = get_safe_version(self.repo_id, self.revision, token=token)
 
-            self._pull_from_repo(allow_patterns="meta/")
+            self._pull_from_repo(allow_patterns="meta/", token=token)
             self._load_metadata()
 
     def _flush_metadata_buffer(self) -> None:
@@ -220,7 +229,10 @@ class LeRobotDatasetMetadata:
         self,
         allow_patterns: list[str] | str | None = None,
         ignore_patterns: list[str] | str | None = None,
+        *,
+        token: str | bool | None = None,
     ) -> None:
+        token_kwargs = {} if token is None else {"token": token}
         if self._requested_root is None:
             self.root = Path(
                 snapshot_download(
@@ -230,6 +242,7 @@ class LeRobotDatasetMetadata:
                     cache_dir=HF_LEROBOT_HUB_CACHE,
                     allow_patterns=allow_patterns,
                     ignore_patterns=ignore_patterns,
+                    **token_kwargs,
                 )
             )
             return
@@ -242,6 +255,7 @@ class LeRobotDatasetMetadata:
             local_dir=self._requested_root,
             allow_patterns=allow_patterns,
             ignore_patterns=ignore_patterns,
+            **token_kwargs,
         )
         self.root = self._requested_root
 

src/lerobot/datasets/lerobot_dataset.py

@@ -65,6 +65,8 @@ class LeRobotDataset(torch.utils.data.Dataset):
         encoder_threads: int | None = None,
         streaming_encoding: bool = False,
         encoder_queue_maxsize: int = 30,
+        *,
+        token: str | bool | None = None,
     ):
         """
         2 modes are available for instantiating this class, depending on 2 different use cases:
@@ -197,6 +199,11 @@ class LeRobotDataset(torch.utils.data.Dataset):
                 instead of writing PNG images first. This makes save_episode() near-instant. Defaults to False.
             encoder_queue_maxsize (int, optional): Maximum number of frames to buffer per camera when using
                 streaming encoding. Defaults to 30 (~1s at 30fps).
+            token: Authentication token used while downloading this dataset
+                from the Hub. Pass a string token, ``True`` to require the
+                locally stored token, ``False`` to disable authentication, or
+                ``None`` to use the Hugging Face Hub default. The token is not
+                retained on the dataset instance after initialization.
 
         Note:
             Write-mode parameters (``streaming_encoding``, ``batch_encoding_size``) passed to
@@ -220,7 +227,11 @@ class LeRobotDataset(torch.utils.data.Dataset):
 
         # Load metadata (sets self.root once from the resolved metadata root)
         self.meta = LeRobotDatasetMetadata(
-            self.repo_id, self._requested_root, self.revision, force_cache_sync=force_cache_sync
+            self.repo_id,
+            self._requested_root,
+            self.revision,
+            force_cache_sync=force_cache_sync,
+            token=token,
         )
         self.root = self.meta.root
         self.revision = self.meta.revision
@@ -260,8 +271,11 @@ class LeRobotDataset(torch.utils.data.Dataset):
         # Load actual data
         if force_cache_sync or not self.reader.try_load():
             if is_valid_version(self.revision):
-                self.revision = get_safe_version(self.repo_id, self.revision)
-            self._download(download_videos)
+                if token is None:
+                    self.revision = get_safe_version(self.repo_id, self.revision)
+                else:
+                    self.revision = get_safe_version(self.repo_id, self.revision, token=token)
+            self._download(download_videos, token=token)
             self.reader.load_and_activate()
 
         # Detect write-mode params for backward compatibility
@@ -626,10 +640,11 @@ class LeRobotDataset(torch.utils.data.Dataset):
                 hub_api.delete_tag(self.repo_id, tag=CODEBASE_VERSION, repo_type="dataset")
             hub_api.create_tag(self.repo_id, tag=CODEBASE_VERSION, revision=branch, repo_type="dataset")
 
-    def _download(self, download_videos: bool = True) -> None:
+    def _download(self, download_videos: bool = True, *, token: str | bool | None = None) -> None:
         """Downloads the dataset from the given 'repo_id' at the provided version."""
         ignore_patterns = None if download_videos else "videos/"
         files = None
+        token_kwargs = {} if token is None else {"token": token}
         if self.episodes is not None:
             # Reader is guaranteed to exist here (created in __init__ before _download)
             files = self.reader.get_episodes_file_paths()
@@ -643,6 +658,7 @@ class LeRobotDataset(torch.utils.data.Dataset):
                     cache_dir=HF_LEROBOT_HUB_CACHE,
                     allow_patterns=files,
                     ignore_patterns=ignore_patterns,
+                    **token_kwargs,
                 )
             )
         else:
@@ -654,6 +670,7 @@ class LeRobotDataset(torch.utils.data.Dataset):
                 local_dir=self._requested_root,
                 allow_patterns=files,
                 ignore_patterns=ignore_patterns,
+                **token_kwargs,
             )
             self.meta.root = self._requested_root
 
@@ -793,6 +810,8 @@ class LeRobotDataset(torch.utils.data.Dataset):
         image_writer_threads: int = 0,
         streaming_encoding: bool = False,
         encoder_queue_maxsize: int = 30,
+        *,
+        token: str | bool | None = None,
     ) -> "LeRobotDataset":
         """Resume recording on an existing dataset.
 
@@ -826,6 +845,8 @@ class LeRobotDataset(torch.utils.data.Dataset):
             streaming_encoding: If ``True``, encode video in real-time during
                 capture.
             encoder_queue_maxsize: Max buffered frames per camera for streaming.
+            token: Authentication token used if metadata must be downloaded
+                from the Hub. The token is not retained on the dataset instance.
 
         Returns:
             A :class:`LeRobotDataset` in write mode, ready to append episodes.
@@ -854,7 +875,11 @@ class LeRobotDataset(torch.utils.data.Dataset):
 
         # Load metadata (revision-safe when root is not provided)
         obj.meta = LeRobotDatasetMetadata(
-            obj.repo_id, obj._requested_root, obj.revision, force_cache_sync=force_cache_sync
+            obj.repo_id,
+            obj._requested_root,
+            obj.revision,
+            force_cache_sync=force_cache_sync,
+            token=token,
         )
 
         obj._encoder_threads = encoder_threads

src/lerobot/datasets/multi_dataset.py

@@ -48,6 +48,8 @@ class MultiLeRobotDataset(torch.utils.data.Dataset):
         tolerances_s: dict | None = None,
         download_videos: bool = True,
         video_backend: str | None = None,
+        *,
+        token: str | bool | None = None,
     ):
         super().__init__()
         self.repo_ids = repo_ids
@@ -65,6 +67,7 @@ class MultiLeRobotDataset(torch.utils.data.Dataset):
                 tolerance_s=self.tolerances_s[repo_id],
                 download_videos=download_videos,
                 video_backend=video_backend,
+                token=token,
             )
             for repo_id in repo_ids
         ]

src/lerobot/datasets/streaming_dataset.py

@@ -256,6 +256,8 @@ class StreamingLeRobotDataset(torch.utils.data.IterableDataset):
         shuffle: bool = True,
         return_uint8: bool = False,
         depth_output_unit: str = DEFAULT_DEPTH_UNIT,
+        *,
+        token: str | bool | None = None,
     ):
         """Initialize a StreamingLeRobotDataset.
 
@@ -278,6 +280,11 @@ class StreamingLeRobotDataset(torch.utils.data.IterableDataset):
             shuffle (bool, optional): Whether to shuffle the dataset across exhaustions. Defaults to True.
             depth_output_unit (str, optional): Physical unit depth maps are dequantized to ("m" or "mm").
                 Defaults to "mm".
+            token: Authentication token used while streaming this dataset from
+                the Hub. Pass a string token, ``True`` to require the locally
+                stored token, ``False`` to disable authentication, or ``None``
+                to use the Hugging Face Hub default. The token is not retained
+                on the dataset instance after initialization.
         """
         super().__init__()
         self.repo_id = repo_id
@@ -306,7 +313,11 @@ class StreamingLeRobotDataset(torch.utils.data.IterableDataset):
 
         # Load metadata
         self.meta = LeRobotDatasetMetadata(
-            self.repo_id, self._requested_root, self.revision, force_cache_sync=force_cache_sync
+            self.repo_id,
+            self._requested_root,
+            self.revision,
+            force_cache_sync=force_cache_sync,
+            token=token,
         )
         self.root = self.meta.root
         self.revision = self.meta.revision
@@ -334,12 +345,14 @@ class StreamingLeRobotDataset(torch.utils.data.IterableDataset):
             self.delta_timestamps = delta_timestamps
             self.delta_indices = get_delta_indices(self.delta_timestamps, self.fps)
 
+        token_kwargs = {} if token is None or self.streaming_from_local else {"token": token}
         self.hf_dataset: datasets.IterableDataset = load_dataset(
             self.repo_id if not self.streaming_from_local else str(self.root),
             split="train",
             streaming=self.streaming,
             data_files="data/*/*.parquet",
             revision=self.revision,
+            **token_kwargs,
         )
 
         self.num_shards = min(self.hf_dataset.num_shards, max_num_shards)

src/lerobot/datasets/utils.py

@@ -325,16 +325,19 @@ def check_version_compatibility(
         logging.warning(FUTURE_MESSAGE.format(repo_id=repo_id, version=v_check))
 
 
-def get_repo_versions(repo_id: str) -> list[packaging.version.Version]:
+def get_repo_versions(repo_id: str, *, token: str | bool | None = None) -> list[packaging.version.Version]:
     """Return available valid versions (branches and tags) on a given Hub repo.
 
     Args:
         repo_id (str): The repository ID on the Hugging Face Hub.
+        token: Authentication token used for Hub requests. Pass a string token,
+            ``True`` to require the locally stored token, ``False`` to disable
+            authentication, or ``None`` to use the Hugging Face Hub default.
 
     Returns:
         list[packaging.version.Version]: A list of valid versions found.
     """
-    api = HfApi()
+    api = HfApi() if token is None else HfApi(token=token)
     repo_refs = api.list_repo_refs(repo_id, repo_type="dataset")
     repo_refs = [b.name for b in repo_refs.branches + repo_refs.tags]
     repo_versions = []
@@ -345,7 +348,12 @@ def get_repo_versions(repo_id: str) -> list[packaging.version.Version]:
     return repo_versions
 
 
-def get_safe_version(repo_id: str, version: str | packaging.version.Version) -> str:
+def get_safe_version(
+    repo_id: str,
+    version: str | packaging.version.Version,
+    *,
+    token: str | bool | None = None,
+) -> str:
     """Return the specified version if available on repo, or the latest compatible one.
 
     If the exact version is not found, it looks for the latest version with the
@@ -354,6 +362,7 @@ def get_safe_version(repo_id: str, version: str | packaging.version.Version) ->
     Args:
         repo_id (str): The repository ID on the Hugging Face Hub.
         version (str | packaging.version.Version): The target version.
+        token: Authentication token forwarded to the Hub version lookup.
 
     Returns:
         str: The safe version string (e.g., "v1.2.3") to use as a revision.
@@ -366,7 +375,7 @@ def get_safe_version(repo_id: str, version: str | packaging.version.Version) ->
     target_version = (
         packaging.version.parse(version) if not isinstance(version, packaging.version.Version) else version
     )
-    hub_versions = get_repo_versions(repo_id)
+    hub_versions = get_repo_versions(repo_id) if token is None else get_repo_versions(repo_id, token=token)
 
     if not hub_versions:
         raise RevisionNotFoundError(

tests/datasets/test_dataset_utils.py

@@ -14,16 +14,21 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+from types import SimpleNamespace
+from unittest.mock import Mock
+
 import pytest
 import torch
+from packaging.version import Version
 
 pytest.importorskip("datasets", reason="datasets is required (install lerobot[dataset])")
 
 from datasets import Dataset  # noqa: E402
 from huggingface_hub import DatasetCard
 
+import lerobot.datasets.utils as dataset_utils
 from lerobot.datasets.io_utils import hf_transform_to_torch
-from lerobot.datasets.utils import create_lerobot_dataset_card
+from lerobot.datasets.utils import create_lerobot_dataset_card, get_repo_versions, get_safe_version
 from lerobot.utils.constants import ACTION, OBS_IMAGES
 from lerobot.utils.feature_utils import combine_feature_dicts
 
@@ -57,6 +62,30 @@ def test_default_parameters():
     ]
 
 
+@pytest.mark.parametrize("token", ["hf_test_token", True, False])
+def test_get_repo_versions_forwards_token(monkeypatch, token):
+    api = Mock()
+    api.list_repo_refs.return_value = SimpleNamespace(
+        branches=[SimpleNamespace(name="v3.0")],
+        tags=[],
+    )
+    hf_api = Mock(return_value=api)
+    monkeypatch.setattr(dataset_utils, "HfApi", hf_api)
+
+    assert get_repo_versions("private/repo", token=token) == [Version("3.0")]
+    hf_api.assert_called_once_with(token=token)
+    api.list_repo_refs.assert_called_once_with("private/repo", repo_type="dataset")
+
+
+@pytest.mark.parametrize("token", ["hf_test_token", True, False])
+def test_get_safe_version_forwards_token(monkeypatch, token):
+    get_versions = Mock(return_value=[Version("3.0")])
+    monkeypatch.setattr(dataset_utils, "get_repo_versions", get_versions)
+
+    assert get_safe_version("private/repo", "v3.0", token=token) == "v3.0"
+    get_versions.assert_called_once_with("private/repo", token=token)
+
+
 def test_with_tags():
     tags = ["tag1", "tag2"]
     card = create_lerobot_dataset_card(tags=tags)

tests/datasets/test_lerobot_dataset.py

@@ -20,6 +20,7 @@ property delegation, and the full create-record-finalize-read lifecycle.
 """
 
 from pathlib import Path
+from types import SimpleNamespace
 from unittest.mock import Mock
 
 import pytest
@@ -191,6 +192,48 @@ def test_metadata_without_root_uses_hub_cache_snapshot_download(
     }
 
 
+@pytest.mark.parametrize("token", ["hf_test_token", True, False])
+def test_metadata_download_forwards_token(tmp_path, monkeypatch, token):
+    snapshot_root = tmp_path / "snapshot"
+    snapshot_download = Mock(return_value=str(snapshot_root))
+    get_safe_version = Mock(return_value="v3.0")
+    load_metadata = Mock(side_effect=[FileNotFoundError, None])
+    monkeypatch.setattr(dataset_metadata_module, "snapshot_download", snapshot_download)
+    monkeypatch.setattr(dataset_metadata_module, "get_safe_version", get_safe_version)
+    monkeypatch.setattr(LeRobotDatasetMetadata, "_load_metadata", load_metadata)
+
+    meta = LeRobotDatasetMetadata(
+        repo_id=DUMMY_REPO_ID,
+        revision="v3.0",
+        token=token,
+    )
+
+    assert meta.root == snapshot_root
+    assert not hasattr(meta, "_token")
+    get_safe_version.assert_called_once_with(DUMMY_REPO_ID, "v3.0", token=token)
+    assert snapshot_download.call_args.kwargs["token"] is token
+
+
+@pytest.mark.parametrize("token", ["hf_test_token", True, False])
+def test_data_download_forwards_token(tmp_path, monkeypatch, token):
+    snapshot_root = tmp_path / "snapshot"
+    snapshot_download = Mock(return_value=str(snapshot_root))
+    monkeypatch.setattr(lerobot_dataset_module, "snapshot_download", snapshot_download)
+
+    dataset = LeRobotDataset.__new__(LeRobotDataset)
+    dataset.repo_id = DUMMY_REPO_ID
+    dataset.revision = "main"
+    dataset.episodes = None
+    dataset._requested_root = None
+    dataset.meta = SimpleNamespace(root=None)
+    dataset.reader = SimpleNamespace(root=None)
+
+    dataset._download(token=token)
+
+    assert dataset.root == snapshot_root
+    assert snapshot_download.call_args.kwargs["token"] is token
+
+
 def test_without_root_reads_different_revisions_from_distinct_snapshot_roots(
     tmp_path,
     info_factory,

tests/datasets/test_streaming.py

@@ -13,12 +13,16 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+from types import SimpleNamespace
+from unittest.mock import Mock
+
 import numpy as np
 import pytest
 import torch
 
 pytest.importorskip("datasets", reason="datasets is required (install lerobot[dataset])")
 
+import lerobot.datasets.streaming_dataset as streaming_dataset_module
 from lerobot.datasets.streaming_dataset import StreamingLeRobotDataset
 from lerobot.datasets.utils import safe_shard
 from lerobot.utils.constants import ACTION
@@ -71,6 +75,40 @@ def get_frames_expected_order(streaming_ds: StreamingLeRobotDataset) -> list[int
     return expected_indices
 
 
+@pytest.mark.parametrize("token", ["hf_test_token", True, False])
+@pytest.mark.parametrize("from_local", [False, True])
+def test_streaming_dataset_forwards_hub_token_only_for_remote_data(tmp_path, monkeypatch, token, from_local):
+    requested_root = tmp_path / "local" if from_local else None
+    metadata = SimpleNamespace(
+        root=requested_root or tmp_path / "snapshot",
+        revision=streaming_dataset_module.CODEBASE_VERSION,
+        _version=streaming_dataset_module.CODEBASE_VERSION,
+        features={},
+        depth_keys=[],
+        image_keys=[],
+        rescale_depth_stats=Mock(),
+    )
+    metadata_cls = Mock(return_value=metadata)
+    load_dataset = Mock(return_value=SimpleNamespace(num_shards=1))
+    monkeypatch.setattr(streaming_dataset_module, "LeRobotDatasetMetadata", metadata_cls)
+    monkeypatch.setattr(streaming_dataset_module, "load_dataset", load_dataset)
+
+    dataset = StreamingLeRobotDataset(DUMMY_REPO_ID, root=requested_root, token=token)
+
+    metadata_cls.assert_called_once_with(
+        DUMMY_REPO_ID,
+        requested_root,
+        streaming_dataset_module.CODEBASE_VERSION,
+        force_cache_sync=False,
+        token=token,
+    )
+    if from_local:
+        assert "token" not in load_dataset.call_args.kwargs
+    else:
+        assert load_dataset.call_args.kwargs["token"] is token
+    assert not hasattr(dataset, "_token")
+
+
 def test_single_frame_consistency(tmp_path, lerobot_dataset_factory):
     """Test if are correctly accessed"""
     ds_num_frames = 400