add suggestions from coderabbit

michaelfeil · michaelfeil · commit 560b5033a584 · 2026-02-03T15:30:31.000-08:00
Signed-off-by: michaelfeil &lt;63565275+michaelfeil@users.noreply.github.com&gt;
diff --git a/modelopt/torch/utils/dataset_utils.py b/modelopt/torch/utils/dataset_utils.py
@@ -119,7 +119,7 @@ def _third_party_get_dataset_samples(
     for text: no tokenization is done and plain text is still returned.
     """
     warn(
-        f"Loading third-party datset {dataset_name} with the split `train`, as the dataset is not registered in {get_supported_datasets()}."
+        f"Loading third-party dataset {dataset_name} with the split `train`, as the dataset is not registered in {get_supported_datasets()}."
     )
     from datasets import load_dataset
 

Original file line number	Diff line number	Diff line change
`@@ -119,7 +119,7 @@ def _third_party_get_dataset_samples(`
`119`	`119`	`for text: no tokenization is done and plain text is still returned.`
`120`	`120`	`"""`
`121`	`121`	`warn(`
`122`		- f"Loading third-party datset {dataset_name} with the split `train`, as the dataset is not registered in {get_supported_datasets()}."
	`122`	+ f"Loading third-party dataset {dataset_name} with the split `train`, as the dataset is not registered in {get_supported_datasets()}."
`123`	`123`	`)`
`124`	`124`	`from datasets import load_dataset`
`125`	`125`