admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-08-06 08:29:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(Train): enable buckets with streaming dataset (#4312)

Browse Source
This commit is contained in:
Steven Palma
2026-08-03 16:00:48 +02:00
committed by GitHub
parent f1efa588b8
commit e867359d09
4 changed files with 57 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/configs/test_default.py
+19
View File
@@ -36,3 +36,22 @@ def test_dataset_config_none_episodes_ok():
def test_dataset_config_empty_episodes_ok():
DatasetConfig(repo_id="user/repo", episodes=[])
def test_dataset_config_bucket_streaming_ok():
DatasetConfig(repo_id="user/repo", repo_type="bucket", streaming=True)
def test_dataset_config_invalid_repo_type():
with pytest.raises(ValueError, match="repo_type"):
DatasetConfig(repo_id="user/repo", repo_type="model")
def test_dataset_config_bucket_requires_streaming():
with pytest.raises(ValueError, match="streaming-only"):
DatasetConfig(repo_id="user/repo", repo_type="bucket")
def test_dataset_config_bucket_rejects_eval_split():
with pytest.raises(ValueError, match="eval_split"):
DatasetConfig(repo_id="user/repo", repo_type="bucket", streaming=True, eval_split=0.1)