diff --git a/neural_compressor/transformers/models/modeling_auto.py b/neural_compressor/transformers/models/modeling_auto.py index 364b991caa8..9a8e5d62a72 100644 --- a/neural_compressor/transformers/models/modeling_auto.py +++ b/neural_compressor/transformers/models/modeling_auto.py @@ -409,6 +409,7 @@ def load_low_bit(cls, pretrained_model_name_or_path, *model_args, **kwargs): user_agent=user_agent, revision=revision, commit_hash=commit_hash, + is_remote_code=True, ) is_sharded = sharded_metadata is not None resolved_archive_file = checkpoint_files if is_sharded else checkpoint_files[0]