[`chore`] Update warning text, a word was missing (#28017)

Update warning, a word was missing

src/transformers/models/llama/modeling_llama.py

@@ -291,8 +291,8 @@ class LlamaAttention(nn.Module):
         self.layer_idx = layer_idx
         if layer_idx is None:
             logger.warning_once(
-                f"Instantiating {self.__class__.__name__} without passing `layer_idx` is not recommended and will "
-                "to errors during the forward call, if caching is used. Please make sure to provide a `layer_idx` "
+                f"Instantiating {self.__class__.__name__} without passing a `layer_idx` is not recommended and will "
+                "lead to errors during the forward call if caching is used. Please make sure to provide a `layer_idx` "
                 "when creating this class."
             )
 

src/transformers/models/mistral/modeling_mistral.py

@@ -202,8 +202,8 @@ class MistralAttention(nn.Module):
         self.layer_idx = layer_idx
         if layer_idx is None:
             logger.warning_once(
-                f"Instantiating {self.__class__.__name__} without passing `layer_idx` is not recommended and will "
-                "to errors during the forward call, if caching is used. Please make sure to provide a `layer_idx` "
+                f"Instantiating {self.__class__.__name__} without passing a `layer_idx` is not recommended and will "
+                "lead to errors during the forward call if caching is used. Please make sure to provide a `layer_idx` "
                 "when creating this class."
             )
 

src/transformers/models/mixtral/modeling_mixtral.py

@@ -246,8 +246,8 @@ class MixtralAttention(nn.Module):
         self.layer_idx = layer_idx
         if layer_idx is None:
             logger.warning_once(
-                f"Instantiating {self.__class__.__name__} without passing `layer_idx` is not recommended and will "
-                "to errors during the forward call, if caching is used. Please make sure to provide a `layer_idx` "
+                f"Instantiating {self.__class__.__name__} without passing a `layer_idx` is not recommended and will "
+                "lead to errors during the forward call if caching is used. Please make sure to provide a `layer_idx` "
                 "when creating this class."
             )
 

src/transformers/models/persimmon/modeling_persimmon.py

@@ -185,8 +185,8 @@ class PersimmonAttention(nn.Module):
         self.layer_idx = layer_idx
         if layer_idx is None:
             logger.warning_once(
-                f"Instantiating {self.__class__.__name__} without passing `layer_idx` is not recommended and will "
-                "to errors during the forward call, if caching is used. Please make sure to provide a `layer_idx` "
+                f"Instantiating {self.__class__.__name__} without passing a `layer_idx` is not recommended and will "
+                "lead to errors during the forward call if caching is used. Please make sure to provide a `layer_idx` "
                 "when creating this class."
             )
 

src/transformers/models/phi/modeling_phi.py

@@ -237,8 +237,8 @@ class PhiAttention(nn.Module):
         self.layer_idx = layer_idx
         if layer_idx is None:
             logger.warning_once(
-                f"Instantiating {self.__class__.__name__} without passing `layer_idx` is not recommended and will "
-                "to errors during the forward call, if caching is used. Please make sure to provide a `layer_idx` "
+                f"Instantiating {self.__class__.__name__} without passing a `layer_idx` is not recommended and will "
+                "lead to errors during the forward call if caching is used. Please make sure to provide a `layer_idx` "
                 "when creating this class."
             )