style

tests/test_activation_offloading.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 import torch
 from torch import nn
 from transformers import AutoModelForCausalLM

tests/test_best_of_n_sampler.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 import torch
 from transformers import AutoTokenizer, GenerationConfig
 

tests/test_cli.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 import os
 from io import StringIO
 from unittest.mock import patch

tests/test_collators.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 import torch
 
 from trl.trainer.dpo_trainer import DataCollatorForPreference

tests/test_core.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 import torch
 
 from trl.core import masked_mean, masked_var, masked_whiten

tests/test_cpo_trainer.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 import torch
 from datasets import load_dataset
 from parameterized import parameterized

tests/test_kto_trainer.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 import pytest
 import torch
 from datasets import load_dataset

tests/test_modeling_geometric_mixture_wrapper.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 import torch
 from transformers import AutoModelForCausalLM, GenerationConfig
 

tests/test_nash_md_trainer.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 from datasets import load_dataset
 from parameterized import parameterized
 from transformers import AutoModelForCausalLM, AutoModelForSequenceClassification, AutoTokenizer

tests/test_orpo_trainer.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 import torch
 from datasets import load_dataset
 from parameterized import parameterized

tests/test_ppo_trainer.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 import torch
 from datasets import load_dataset
 from transformers import AutoModelForCausalLM, AutoModelForSequenceClassification, AutoTokenizer

tests/test_rewards.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 from trl.rewards import get_soft_overlong_punishment, think_format_reward
 
 from .testing_utils import TrlTestCase

tests/test_rich_progress_callback.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 import torch
 import torch.nn as nn
 from datasets import Dataset

tests/test_trainers_args.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 from datasets import load_dataset
 from parameterized import parameterized
 from transformers import AutoModelForCausalLM, AutoModelForSequenceClassification, AutoTokenizer

tests/test_xpo_trainer.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 from datasets import load_dataset
 from parameterized import parameterized
 from transformers import AutoModelForCausalLM, AutoModelForSequenceClassification, AutoTokenizer

trl/core.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 import numpy as np
 import torch
 from accelerate import logging

trl/experimental/bema_for_ref_model/callback.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 import logging
 
 import torch

trl/experimental/gspo_token/grpo_trainer.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 import torch
 
 from trl import GRPOTrainer as _GRPOTrainer

trl/rewards/__init__.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 import sys
 from typing import TYPE_CHECKING
 

trl/rewards/other_rewards.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 from collections.abc import Callable
 
 

trl/trainer/judges.py

@@ -206,7 +206,8 @@ class PairRMJudge(BasePairwiseJudge):
     >>> print(results)  # [0, 1] (indicating the first completion is preferred for the first prompt and the second)
     ```
 
-    > [!TIP] > This class requires the llm-blender library to be installed. Install it with: `pip install llm-blender`.
+    > [!TIP]
+    > This class requires the llm-blender library to be installed. Install it with: `pip install llm-blender`.
     """
 
     def __init__(self):