diff --git a/CHANGELOGS.rst b/CHANGELOGS.rst
index 9ab5c3b2..a0809cb4 100644
--- a/CHANGELOGS.rst
+++ b/CHANGELOGS.rst
@@ -4,6 +4,8 @@ Change Logs
 0.7.11
 ++++++
 
+* :pr:`220`: adds a patch for PR `#40791 <https://github.com/huggingface/transformers/pull/40791>`_ in transformers
+
 0.7.10
 ++++++
 
diff --git a/onnx_diagnostic/torch_export_patches/patches/patch_transformers.py b/onnx_diagnostic/torch_export_patches/patches/patch_transformers.py
index 9a96a2b7..e95a0a47 100644
--- a/onnx_diagnostic/torch_export_patches/patches/patch_transformers.py
+++ b/onnx_diagnostic/torch_export_patches/patches/patch_transformers.py
@@ -35,6 +35,9 @@
 from ...ext_test_case import has_transformers
 from ...helpers.torch_helper import is_torchdynamo_exporting
 
+patch_is_initialized = pv.Version(transformers.__version__) > pv.Version("4.56.99")
+
+
 if patch_masking_utils:
     # Introduced in 4.52
     from transformers.masking_utils import (
@@ -213,6 +216,8 @@ def lazy_initialization(self, key_states: torch.Tensor):
             new_shape[-2] = 0
             self.keys = torch.empty(new_shape, dtype=self.dtype, device=self.device)
             self.values = torch.empty(new_shape, dtype=self.dtype, device=self.device)
+            if patch_is_initialized:
+                self.is_initialized = True
 
 
 def _patch_make_causal_mask(
diff --git a/onnx_diagnostic/torch_models/validate.py b/onnx_diagnostic/torch_models/validate.py
index 42d60c1e..d6b3994f 100644
--- a/onnx_diagnostic/torch_models/validate.py
+++ b/onnx_diagnostic/torch_models/validate.py
@@ -113,6 +113,7 @@ def _make_folder_name(
     dtype: Optional[Union[str, torch.dtype]] = None,
     device: Optional[Union[str, torch.device]] = None,
     subfolder: Optional[str] = None,
+    opset: Optional[int] = None,
 ) -> str:
     "Creates a filename unique based on the given options."
     els = [model_id.replace("/", "_")]
@@ -136,6 +137,8 @@ def _make_folder_name(
         else:
             raise AssertionError(f"unexpected value for device={device}, sdev={sdev!r}")
         els.append(sdev)
+    if opset is not None:
+        els.append(f"op{opset}")
     return "-".join(els)
 
 
@@ -412,7 +415,13 @@ def validate_model(
     folder_name = None
     if dump_folder:
         folder_name = _make_folder_name(
-            model_id, exporter, optimization, dtype=dtype, device=device, subfolder=subfolder
+            model_id,
+            exporter,
+            optimization,
+            dtype=dtype,
+            device=device,
+            subfolder=subfolder,
+            opset=opset,
         )
         dump_folder = os.path.join(dump_folder, folder_name)
         if not os.path.exists(dump_folder):
@@ -1509,6 +1518,8 @@ def call_torch_export_custom(
         "default+onnxruntime+os_ort",
         None,
     }
+    if optimization == "none":
+        optimization = ""
     assert (
         optimization in available
     ), f"unexpected value for optimization={optimization}, available={available}"