fix: Adjustments in _prepare_input_and_invoke_stream for meta models

libs/aws/langchain_aws/llms/bedrock.py

@@ -991,11 +991,7 @@ async def _aprepare_input_and_invoke_stream(
         _model_kwargs = self.model_kwargs or {}
         provider = self._get_provider()
 
-        if stop:
-            if provider not in self.provider_stop_sequence_key_name_map:
-                raise ValueError(
-                    f"Stop sequence key name for {provider} is not supported."
-                )
+        if stop and provider in self.provider_stop_sequence_key_name_map:
             if k := self.provider_stop_sequence_key_name_map.get(provider):
                 _model_kwargs[k] = stop