UT for src/guidellm/data/deserializers/huggingface.py (#500)

## Summary

<!--
Include a short paragraph of the changes introduced in this PR.
If this PR requires additional context or rationale, explain why
the changes are necessary.
-->

pytest tests/unit/data/deserializers/test_huggingface.py

## Details

<!--
Provide a detailed list of all changes introduced in this pull request.
-->
- [ ]

## Test Plan

<!--
List the steps needed to test this PR.
-->
-

## Related Issues

<!--
Link any relevant issues that this PR addresses.
-->
- Resolves #

---

- [ ] "I certify that all code in this PR is my own, except as noted
below."

## Use of AI

- [ ] Includes AI-assisted code completion
- [ ] Includes code generated by an AI application
- [ ] Includes AI-generated tests (NOTE: AI written tests should have a
docstring that includes `## WRITTEN BY AI ##`)

Author: sjmonson

tests/unit/data/deserializers/test_huggingface.py

@@ -0,0 +1,61 @@
+import pytest
+from datasets import Dataset
+
+from guidellm.data.deserializers.huggingface import (
+    HuggingFaceDatasetDeserializer,
+)
+
+
+@pytest.fixture
+def processor_factory():
+    return None
+
+
+@pytest.fixture
+def deserializer():
+    return HuggingFaceDatasetDeserializer()
+
+
+def test_hf_dataset_direct_return(deserializer, processor_factory):
+    # build one simple HF dataset
+    data = Dataset.from_dict({"text": ["hello", "world"]})
+    result = deserializer(data, processor_factory, random_seed=42)
+    assert result is data, "return original Dataset object"
+
+
+def test_local_hf_directory_dataset(deserializer, processor_factory, tmp_path):
+    # --- 1. build one simple HF dataset ---
+    dataset = Dataset.from_dict({"id": [1, 2], "text": ["a", "b"]})
+    #  --- 2.  Save to a local directory ---
+    dataset_dir = tmp_path / "local_hf_dataset"
+    dataset.save_to_disk(dataset_dir)
+
+    # --- 3. call HF DatasetDeserializer  ---
+    result = deserializer(
+        dataset_dir,
+        processor_factory,
+        random_seed=123,
+    )
+
+    # --- 4. assertion ---
+    assert isinstance(result, Dataset)
+    assert result["text"] == ["a", "b"]
+
+
+@pytest.mark.parametrize(
+    "internal_ds_name",
+    [
+        "mnist",
+        "imdb",
+    ],
+)
+def test_hf_internal_dataset(deserializer, processor_factory, internal_ds_name):
+    result = deserializer(internal_ds_name, processor_factory, random_seed=42)
+
+    assert isinstance(result, (Dataset | dict)), "HF dataset loading failed"
+    assert "train" in result or isinstance(result, Dataset), (
+        "Expected 'train' split in the loaded dataset"
+    )
+    assert "test" in result or isinstance(result, Dataset), (
+        "Expected 'test' split in the loaded dataset"
+    )