import gradio as gr

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ")