diff --git a/optimum/bettertransformer/models/__init__.py b/optimum/bettertransformer/models/__init__.py
index 1e95c40026e..7f115c27b6b 100644
--- a/optimum/bettertransformer/models/__init__.py
+++ b/optimum/bettertransformer/models/__init__.py
@@ -38,7 +38,7 @@
     BartEncoderLayerBetterTransformer,
     BertLayerBetterTransformer,
     CLIPLayerBetterTransformer,
-    DetrEncoderLayerBetterTransformer
+    DetrEncoderLayerBetterTransformer,
     DistilBertLayerBetterTransformer,
     FSMTEncoderLayerBetterTransformer,
     MBartEncoderLayerBetterTransformer,
diff --git a/optimum/bettertransformer/models/encoder_models.py b/optimum/bettertransformer/models/encoder_models.py
index 0151f67d55e..22f434c528f 100644
--- a/optimum/bettertransformer/models/encoder_models.py
+++ b/optimum/bettertransformer/models/encoder_models.py
@@ -11,7 +11,6 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-from typing import TYPE_CHECKING
 
 import torch
 import torch.nn as nn
@@ -22,10 +21,6 @@
 from .base import BetterTransformerBaseLayer
 
 
-if TYPE_CHECKING:
-    from transformers import PretrainedConfig
-
-
 class AlbertLayerBetterTransformer(BetterTransformerBaseLayer, nn.Module):
     def __init__(self, albert_layer, config):
         r"""