diff --git a/aiserver.py b/aiserver.py
index bb622059..900e6078 100644
--- a/aiserver.py
+++ b/aiserver.py
@@ -2706,7 +2706,7 @@ def load_model(use_gpu=True, gpu_layers=None, disk_layers=None, initial_load=Fal
                                 shutil.move(os.path.realpath(huggingface_hub.hf_hub_download(koboldai_vars.model, transformers.configuration_utils.CONFIG_NAME, revision=koboldai_vars.revision, cache_dir="cache", local_files_only=True, legacy_cache_layout=legacy)), os.path.join("models/{}".format(koboldai_vars.model.replace('/', '_')), transformers.configuration_utils.CONFIG_NAME))
                                 if(utils.num_shards is None):
                                     # Save the pytorch_model.bin of an unsharded model
-                                    shutil.move(os.path.realpath(huggingface_hub.hf_hub_download(koboldai_vars.model, transformers.modeling_utils.WEIGHTS_NAME, revision=koboldai_vars.revision, cache_dir="cache", local_files_only=True, legacy_cache_layout=legacy)), os.path.join("models/{}".format(vars.model.replace('/', '_')), transformers.modeling_utils.WEIGHTS_NAME))
+                                    shutil.move(os.path.realpath(huggingface_hub.hf_hub_download(koboldai_vars.model, transformers.modeling_utils.WEIGHTS_NAME, revision=koboldai_vars.revision, cache_dir="cache", local_files_only=True, legacy_cache_layout=legacy)), os.path.join("models/{}".format(koboldai_vars.model.replace('/', '_')), transformers.modeling_utils.WEIGHTS_NAME))
                                 else:
                                     with open(utils.from_pretrained_index_filename) as f:
                                         map_data = json.load(f)