[modeling_utils] rearrange text (#16632)

src/transformers/modeling_utils.py

@@ -1487,12 +1487,6 @@ class PreTrainedModel(nn.Module, ModuleUtilsMixin, GenerationMixin, PushToHubMix
                 Please refer to the mirror site for more information.
             _fast_init(`bool`, *optional*, defaults to `True`):
                 Whether or not to disable fast initialization.
-            low_cpu_mem_usage(`bool`, *optional*, defaults to `False`):
-                Tries to not use more than 1x model size in CPU memory (including peak memory) while loading the model.
-                This is an experimental feature and a subject to change at any moment.
-            torch_dtype (`str` or `torch.dtype`, *optional*):
-                Override the default `torch.dtype` and load the model under this dtype. If `"auto"` is passed the dtype
-                will be automatically derived from the model's weights.
 
                 <Tip warning={true}>
 
@@ -1502,6 +1496,12 @@ class PreTrainedModel(nn.Module, ModuleUtilsMixin, GenerationMixin, PushToHubMix
 
                 </Tip>
 
+            low_cpu_mem_usage(`bool`, *optional*, defaults to `False`):
+                Tries to not use more than 1x model size in CPU memory (including peak memory) while loading the model.
+                This is an experimental feature and a subject to change at any moment.
+            torch_dtype (`str` or `torch.dtype`, *optional*):
+                Override the default `torch.dtype` and load the model under this dtype. If `"auto"` is passed the dtype
+                will be automatically derived from the model's weights.
             kwargs (remaining dictionary of keyword arguments, *optional*):
                 Can be used to update the configuration object (after it being loaded) and initiate the model (e.g.,
                 `output_attentions=True`). Behaves differently depending on whether a `config` is provided or