Consistency regarding relative imports (#4498)

Author: qgallouedec

trl/experimental/grpo_with_replay_buffer/grpo_with_replay_buffer_config.py

@@ -14,7 +14,7 @@
 
 from dataclasses import dataclass, field
 
-from trl.trainer.grpo_config import GRPOConfig
+from ...trainer.grpo_config import GRPOConfig
 
 
 @dataclass

trl/experimental/grpo_with_replay_buffer/grpo_with_replay_buffer_trainer.py

@@ -18,14 +18,9 @@
 import torch
 from accelerate.utils import gather_object
 
-from trl.data_utils import (
-    apply_chat_template,
-    is_conversational,
-    prepare_multimodal_messages,
-)
-from trl.trainer.grpo_trainer import GRPOTrainer
-from trl.trainer.utils import nanmax, nanmin, nanstd, pad
-
+from ...data_utils import apply_chat_template, is_conversational, prepare_multimodal_messages
+from ...trainer.grpo_trainer import GRPOTrainer
+from ...trainer.utils import nanmax, nanmin, nanstd, pad
 from .grpo_with_replay_buffer_config import GRPOWithReplayBufferConfig
 
 

trl/experimental/gspo_token/grpo_trainer.py

@@ -14,8 +14,7 @@
 
 import torch
 
-from trl import GRPOTrainer as _GRPOTrainer
-
+from ...trainer.grpo_trainer import GRPOTrainer as _GRPOTrainer
 from ...trainer.utils import nanmax, nanmin
 
 

trl/mergekit_utils.py

@@ -15,7 +15,7 @@
 import torch
 from huggingface_hub import HfApi
 
-from trl.import_utils import is_mergekit_available
+from .import_utils import is_mergekit_available
 
 
 if is_mergekit_available():

trl/rewards/accuracy_rewards.py

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from trl.import_utils import is_math_verify_available
+from ..import_utils import is_math_verify_available
 
 
 if is_math_verify_available():

trl/trainer/nash_md_config.py

@@ -14,7 +14,7 @@
 
 from dataclasses import dataclass, field
 
-from trl.trainer.online_dpo_config import OnlineDPOConfig
+from .online_dpo_config import OnlineDPOConfig
 
 
 @dataclass