diff --git a/configuration_mixformer_sequential.py b/configuration_mixformer_sequential.py
index 7366275..e80206a 100644
--- a/configuration_mixformer_sequential.py
+++ b/configuration_mixformer_sequential.py
@@ -21,24 +21,24 @@ class MixFormerSequentialConfig(PretrainedConfig):
 
     def __init__(
         self,
-        vocab_size: Optional[int] = 50304,
-        n_positions: Optional[int] = 2048,
-        n_embd: Optional[int] = 1024,
-        n_layer: Optional[int] = 20,
+        vocab_size: int = 50304,
+        n_positions: int = 2048,
+        n_embd: int = 1024,
+        n_layer: int = 20,
         n_inner: Optional[int] = None,
-        n_head: Optional[int] = 16,
+        n_head: int = 16,
         n_head_kv: Optional[int] = None,
         rotary_dim: Optional[int] = 32,
         activation_function: Optional[str] = "gelu_new",
         flash_rotary: bool = False,
         fused_dense: bool = False,
-        attn_pdrop: Optional[float] = 0.0,
-        embd_pdrop: Optional[float] = 0.0,
-        resid_pdrop: Optional[float] = 0.0,
-        layer_norm_epsilon: Optional[float] = 1e-5,
-        initializer_range: Optional[float] = 0.02,
-        tie_word_embeddings: Optional[bool] = False,
-        pad_vocab_size_multiple: Optional[int] = 64,
+        attn_pdrop: float = 0.0,
+        embd_pdrop: float = 0.0,
+        resid_pdrop: float = 0.0,
+        layer_norm_epsilon: float = 1e-5,
+        initializer_range: float = 0.02,
+        tie_word_embeddings: bool = False,
+        pad_vocab_size_multiple: int = 64,
         **kwargs
     ) -> None:
         self.vocab_size = int(math.ceil(vocab_size / pad_vocab_size_multiple) * pad_vocab_size_multiple)