add clarity in documentation for device_map

Author: sayakpaul

src/diffusers/models/modeling_utils.py

@@ -821,7 +821,10 @@ def from_pretrained(cls, pretrained_model_name_or_path: Optional[Union[str, os.P
 
                 Set `device_map="auto"` to have 🤗 Accelerate automatically compute the most optimized `device_map`. For
                 more information about each option see [designing a device
-                map](https://hf.co/docs/accelerate/main/en/usage_guides/big_modeling#designing-a-device-map).
+                map](https://hf.co/docs/accelerate/main/en/usage_guides/big_modeling#designing-a-device-map). You can
+                also refer to the [Diffusers-specific
+                documentation](https://huggingface.co/docs/diffusers/main/en/training/distributed_inference#model-sharding)
+                for more concrete examples.
             max_memory (`Dict`, *optional*):
                 A dictionary device identifier for the maximum memory. Will default to the maximum memory available for
                 each GPU and the available CPU RAM if unset.