I didn't get this error yesterday when loading the model. What is different about today? where did the pretrained data go? How do I get it back? it does this with any model that previously worked.

INFO:Loading WizardLM-7B-uncensored-GPTQ... WARNING:Applying the monkey patch for using LoRAs in 4-bit mode. It may cause undefined behavior outside its intended scope. Loading Model ... WARNING:The safetensors archive passed at models\WizardLM-7B-uncensored-GPTQ\WizardLM-7B-uncensored-GPTQ-4bit-128g.compat.no-act-order.safetensors does not contain metadata. Make sure to save your model with the save_pretrained method. Defaulting to 'pt' metadata. Loaded the model in 4.85 seconds. INFO:Loaded the model in 4.91 seconds.