search buffers for dtype (#23159)

src/transformers/modeling_utils.py

@@ -207,7 +207,15 @@ def get_parameter_dtype(parameter: Union[nn.Module, GenerationMixin, "ModuleUtil
         # if no floating dtype was found return whatever the first dtype is
         return last_dtype
 
-    else:
+    for t in parameter.buffers():
+        last_dtype = t.dtype
+        if t.is_floating_point():
+            return t.dtype
+
+    if last_dtype is not None:
+        # if no floating dtype was found return whatever the first dtype is
+        return last_dtype
+
     # For nn.DataParallel compatibility in PyTorch > 1.5
     def find_tensor_attributes(module: nn.Module) -> List[Tuple[str, Tensor]]:
         tuples = [(k, v) for k, v in module.__dict__.items() if torch.is_tensor(v)]