riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 02:02:21 +06:00
Code Issues Actions 33 Packages Projects Releases Wiki Activity

Disallow Offload to disk for gguf files (#36933)

Browse Source 
update

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
This commit is contained in:
Mohamed Mekkouri 2025-03-24 19:30:01 +01:00 committed by GitHub
parent 91455c1825
commit 2b8a15cc3f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/transformers/modeling_utils.py
View File

@ -4327,6 +4327,12 @@ class PreTrainedModel(nn.Module, ModuleUtilsMixin, GenerationMixin, PushToHubMix
"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,