diff --git a/.github/workflows/run_tests.yml b/.github/workflows/run_tests.yml
index 52de4dd..bed4606 100644
--- a/.github/workflows/run_tests.yml
+++ b/.github/workflows/run_tests.yml
@@ -7,26 +7,28 @@ jobs:
   run-tests:
     strategy:
       matrix:
-        python-version: [ 3.9, 3.10, 3.11 ]
+        python-version: [3.10, 3.11 ]
         os: [ ubuntu-latest ]
       fail-fast: false
     runs-on: ${{ matrix.os }}
     steps:
       - name: Checkout code
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
 
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          python -m pip install pytest
+          python -m pip install pytest ruff
 
-      - name: Checks with pre-commit
-        uses: pre-commit/action@v2.0.3
+      - name: Lint with Ruff
+        run: |
+          ruff --ignore=F401,E501 --format=github --target-version=py37 .
+        continue-on-error: true
 
       - name: Test with pytest
         run: |
diff --git a/test/test_token_classification/__init__.py b/test/test_token_classification/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/test/test_token_classification/conftest.py b/test/test_token_classification/conftest.py
new file mode 100644
index 0000000..b93a5db
--- /dev/null
+++ b/test/test_token_classification/conftest.py
@@ -0,0 +1,9 @@
+import pytest 
+
+from ua_datasets import MovaInstitutePOSDataset
+
+@pytest.fixture(scope="module")
+def train_dataset(request):
+    root = request.config.getoption("--dataset-root")
+    df = MovaInstitutePOSDataset(root=root)
+    return df
\ No newline at end of file
diff --git a/test/test_token_classification/test_token.py b/test/test_token_classification/test_token.py
new file mode 100644
index 0000000..7b2a5e7
--- /dev/null
+++ b/test/test_token_classification/test_token.py
@@ -0,0 +1,5 @@
+import pytest
+
+@pytest.mark.parametrize("dataset_size", [8_016])
+def test_dataset_size(dataset_size, dataset):
+    assert len(dataset) == dataset_size