Enable PyTests for Nemotron-CC classifiers (#543)

* Enable PyTests for Nemotron-CC classifiers Signed-off-by: Sarah Yurick <[email protected]> * Update copyright year Signed-off-by: Sarah Yurick <[email protected]> * revert pyproject toml change Signed-off-by: Sarah Yurick <[email protected]> * push Signed-off-by: Sarah Yurick <[email protected]> --------- Signed-off-by: Sarah Yurick <[email protected]>
NVIDIA · Feb 18, 2025 · 27de781 · 27de781
1 parent 2391e28
commit 27de781
Show file tree

Hide file tree

Showing 4 changed files with 4 additions and 10 deletions.
diff --git a/nemo_curator/scripts/classifiers/fineweb_mixtral_edu_classifier_inference.py b/nemo_curator/scripts/classifiers/fineweb_mixtral_edu_classifier_inference.py
@@ -1,4 +1,4 @@
-# Copyright (c) 2024, NVIDIA CORPORATION.  All rights reserved.
+# Copyright (c) 2025, NVIDIA CORPORATION.  All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/nemo_curator/scripts/classifiers/fineweb_nemotron_edu_classifier_inference.py b/nemo_curator/scripts/classifiers/fineweb_nemotron_edu_classifier_inference.py
@@ -1,4 +1,4 @@
-# Copyright (c) 2024, NVIDIA CORPORATION.  All rights reserved.
+# Copyright (c) 2025, NVIDIA CORPORATION.  All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/pyproject.toml b/pyproject.toml
@@ -1,4 +1,4 @@
-# Copyright (c) 2024, NVIDIA CORPORATION.  All rights reserved.
+# Copyright (c) 2025, NVIDIA CORPORATION.  All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/tests/test_classifiers.py b/tests/test_classifiers.py
@@ -1,4 +1,4 @@
-# Copyright (c) 2024, NVIDIA CORPORATION.  All rights reserved.
+# Copyright (c) 2025, NVIDIA CORPORATION.  All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -139,9 +139,6 @@ def test_fineweb_edu_classifier(gpu_client, domain_dataset):
     assert result_pred.equals(expected_pred)
 
 
-@pytest.mark.skip(
-    reason="Skipping until https://huggingface.co/nvidia/nemocurator-fineweb-mixtral-edu-classifier is published"
-)
 @pytest.mark.gpu
 def test_fineweb_mixtral_classifier(gpu_client, domain_dataset):
     from nemo_curator.classifiers import FineWebMixtralEduClassifier
@@ -155,9 +152,6 @@ def test_fineweb_mixtral_classifier(gpu_client, domain_dataset):
     assert result_pred.equals(expected_pred)
 
 
-@pytest.mark.skip(
-    reason="Skipping until https://huggingface.co/nvidia/nemocurator-fineweb-nemotron-4-edu-classifier is published"
-)
 @pytest.mark.gpu
 def test_fineweb_nemotron_classifier(gpu_client, domain_dataset):
     from nemo_curator.classifiers import FineWebNemotronEduClassifier