Squashed commit of the following:

commit 65eb45c
Author: Quentin Gallouédec <[email protected]>
Date:   Mon Oct 6 13:07:18 2025 -0600

    Apply style and revert change in `sft_video_llm` example (#4214)

commit ae6837f
Author: Sergio Paniego Blanco <[email protected]>
Date:   Mon Oct 6 18:40:18 2025 +0200

    Removed tokenizer/processor creation from example scripts (#4211)

commit 56a8f11
Author: Albert Villanova del Moral <[email protected]>
Date:   Mon Oct 6 17:45:44 2025 +0200

    Replace setup with pyproject and fix packaging unintended modules (#4194)

commit 5291015
Author: Sergio Paniego Blanco <[email protected]>
Date:   Mon Oct 6 16:04:06 2025 +0200

    Remove `Optional` from `processing_class` in `PPOTrainer` (#4212)

commit 0588b1f
Author: Sergio Paniego Blanco <[email protected]>
Date:   Mon Oct 6 15:57:17 2025 +0200

    Updated vLLM integration guide (#4162)

    Co-authored-by: Quentin Gallouédec <[email protected]>

commit 45ee98b
Author: Albert Villanova del Moral <[email protected]>
Date:   Mon Oct 6 11:14:54 2025 +0200

    Replace unittest with pytest (#4188)

commit 3800a6e
Author: Albert Villanova del Moral <[email protected]>
Date:   Mon Oct 6 11:13:21 2025 +0200

    Hotfix: Exclude transformers 4.57.0 for Python 3.9 (#4209)

    Co-authored-by: Sergio Paniego Blanco <[email protected]>

commit 7ad9ce8
Author: Sergio Paniego Blanco <[email protected]>
Date:   Mon Oct 6 11:04:20 2025 +0200

    Remove tokenizer creation from `sft` example script (#4197)

commit 0c2dc14
Author: Albert Villanova del Moral <[email protected]>
Date:   Mon Oct 6 08:31:58 2025 +0200

    Remove custome_container for building the docs (#4198)

commit ced8b33
Author: burtenshaw <[email protected]>
Date:   Mon Oct 6 08:23:11 2025 +0200

    [DOCS/FIX] lora without regrets - fix lr (#4207)

Author: qgallouedec

examples/scripts/reward_modeling.py

@@ -67,7 +67,6 @@
     get_kbit_device_map,
     get_peft_config,
     get_quantization_config,
-    setup_chat_format,
 )
 
 

examples/scripts/sft_gpt_oss.py

@@ -75,7 +75,6 @@ def main(script_args, training_args, model_args):
 
     model = AutoModelForCausalLM.from_pretrained(model_args.model_name_or_path, **model_kwargs)
 
-
     # Load dataset
     dataset = load_dataset(script_args.dataset_name, name=script_args.dataset_config)
 

tests/test_activation_offloading.py

@@ -151,6 +151,6 @@ def test_real_hf_model(self):
         grads2 = [p.grad.clone() for p in model.parameters()]
 
         # Check outputs and gradients match
-        self.assertTrue(torch.allclose(out1, out2, rtol=1e-5))
+        assert torch.allclose(out1, out2, rtol=1e-5)
         for g1, g2 in zip(grads1, grads2, strict=True):
-            self.assertTrue(torch.allclose(g1, g2, rtol=1e-5))
+            assert torch.allclose(g1, g2, rtol=1e-5)

tests/test_cli.py

@@ -14,9 +14,11 @@
 
 
 import os
+import sys
 from io import StringIO
 from unittest.mock import patch
 
+import pytest
 import yaml
 
 from .testing_utils import TrlTestCase

tests/test_dpo_trainer.py

@@ -13,6 +13,7 @@
 # limitations under the License.
 
 import re
+import sys
 from unittest.mock import MagicMock
 
 import numpy as np

trl/scripts/dpo.py

@@ -80,7 +80,6 @@
     get_peft_config,
     get_quantization_config,
 )
-from trl.trainer.utils import SIMPLE_CHAT_TEMPLATE
 
 
 logger = logging.get_logger(__name__)