diff --git a/libs/vertexai/langchain_google_vertexai/_base.py b/libs/vertexai/langchain_google_vertexai/_base.py
index e7ffc646..fe1793f3 100644
--- a/libs/vertexai/langchain_google_vertexai/_base.py
+++ b/libs/vertexai/langchain_google_vertexai/_base.py
@@ -118,7 +118,7 @@ def validate_params_base(cls, values: dict) -> Any:
         if values.get("client_cert_source"):
             client_options.client_cert_source = values["client_cert_source"]
         values["client_options"] = client_options
-        additional_headers = values.get("additional_headers", {})
+        additional_headers = values.get("additional_headers") or {}
         values["default_metadata"] = tuple(additional_headers.items())
         return values
 
@@ -177,7 +177,7 @@ def _library_version(self) -> str:
 
 class _VertexAICommon(_VertexAIBase):
     client_preview: Any = Field(default=None, exclude=True)  #: :meta private:
-    model_name: str = Field(default=None, alias="model")
+    model_name: Optional[str] = Field(default=None, alias="model")
     "Underlying model name."
     temperature: Optional[float] = None
     "Sampling temperature, it controls the degree of randomness in token selection."
diff --git a/libs/vertexai/langchain_google_vertexai/chat_models.py b/libs/vertexai/langchain_google_vertexai/chat_models.py
index 9f341a3b..2018bd06 100644
--- a/libs/vertexai/langchain_google_vertexai/chat_models.py
+++ b/libs/vertexai/langchain_google_vertexai/chat_models.py
@@ -877,7 +877,7 @@ class Joke(BaseModel):
 
         .. code-block:: python
 
-            'The image is of five blueberry scones arranged on a piece of baking paper. \n\nHere is a list of what is in the picture:\n* **Five blueberry scones:** They are scattered across the parchment paper, dusted with powdered sugar.  \n* **Two cups of coffee:**  Two white cups with saucers. One appears full, the other partially drunk.\n* **A bowl of blueberries:** A brown bowl is filled with fresh blueberries, placed near the scones.\n* **A spoon:**  A silver spoon with the words "Let\'s Jam" rests on the paper.\n* **Pink peonies:** Several pink peonies lie beside the scones, adding a touch of color.\n* **Baking paper:** The scones, cups, bowl, and spoon are arranged on a piece of white baking paper, splattered with purple.  The paper is crinkled and sits on a dark surface. \n\nThe image has a rustic and delicious feel, suggesting a cozy and enjoyable breakfast or brunch setting. \n'
+            'The image is of five blueberry scones arranged on a piece of baking paper. \n\nHere is a list of what is in the picture:\n* **Five blueberry scones:** They are scattered across the parchment paper, dusted with powdered sugar.  \n* **Two cups of coffee:**  Two white cups with saucers. One appears full, the other partially drunk.\n* **A bowl of blueberries:** A brown bowl is filled with fresh blueberries, placed near the scones.\n* **A spoon:**  A silver spoon with the words "Let\'s Jam" rests on the paper.\n* **Pink peonies:** Several pink peonies lie beside the scones, adding a touch of color.\n* **Baking paper:** The scones, cups, bowl, and spoon are arranged on a piece of white baking paper, splattered with purple.  The paper is crinkled and sits on a dark surface. \n\nThe image has a rustic and delicious feel, suggesting a cozy and enjoyable breakfast or brunch setting. \n' # codespell:ignore brunch
 
     Video input:
         **NOTE**: Currently only supported for ``gemini-...-vision`` models.
diff --git a/libs/vertexai/langchain_google_vertexai/model_garden.py b/libs/vertexai/langchain_google_vertexai/model_garden.py
index fd7938d6..8bd92ea2 100644
--- a/libs/vertexai/langchain_google_vertexai/model_garden.py
+++ b/libs/vertexai/langchain_google_vertexai/model_garden.py
@@ -139,8 +139,6 @@ async def _agenerate(
 
 class ChatAnthropicVertex(_VertexAICommon, BaseChatModel):
     async_client: Any = Field(default=None, exclude=True)  #: :meta private:
-    model_name: Optional[str] = Field(default=None, alias="model")  # type: ignore[assignment]
-    "Underlying model name."
     max_output_tokens: int = Field(default=1024, alias="max_tokens")
     access_token: Optional[str] = None
     stream_usage: bool = True  # Whether to include usage metadata in streaming output