Update app.py

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 
-# Use a pipeline as a high-level helper
-from transformers import pipeline
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-pipe = pipeline("text-generation", model="TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ")
+tokenizer = AutoTokenizer.from_pretrained("TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ")
+model = AutoModelForCausalLM.from_pretrained("TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ")