[`bnb`] Fix bnb error message (#22026)

* fix error message

* make style

src/transformers/modeling_utils.py

@@ -2578,8 +2578,11 @@ class PreTrainedModel(nn.Module, ModuleUtilsMixin, GenerationMixin, PushToHubMix
                     raise ValueError(
                         """
                         Some modules are dispatched on the CPU or the disk. Make sure you have enough GPU RAM to fit
-                        the quantized model. If you have set a value for `max_memory` you should increase that. To have
-                        an idea of the modules that are set on the CPU or RAM you can print model.hf_device_map.
+                        the quantized model. If you want to dispatch the model on the CPU or the disk while keeping
+                        these modules in 32-bit, you need to set `load_in_8bit_fp32_cpu_offload=True` and pass a custom
+                        `device_map` to `from_pretrained`. Check
+                        https://huggingface.co/docs/transformers/main/en/main_classes/quantization#offload-between-cpu-and-gpu
+                        for more details.
                         """
                     )
                 del device_map_without_lm_head