Disallow Offload to disk for gguf files (#36933)

update

Co-authored-by: Marc Sun <[email protected]>

Author: MekkCyber

src/transformers/modeling_utils.py

@@ -4327,6 +4327,12 @@ def from_pretrained(
                 "You cannot combine Quantization and loading a model from a GGUF file, try again by making sure you did not passed a `quantization_config` or that you did not load a quantized model from the Hub."
             )
 
+        if gguf_file and device_map is not None and "disk" in device_map.values():
+            raise RuntimeError(
+                "One or more modules is configured to be mapped to disk. Disk offload is not supported for models "
+                "loaded from GGUF files."
+            )
+
         checkpoint_files, sharded_metadata = _get_resolved_checkpoint_files(
             pretrained_model_name_or_path=pretrained_model_name_or_path,
             subfolder=subfolder,