Switched to cpu only...

app.py

@@ -2,6 +2,8 @@ import streamlit as st
 from transformers import pipeline
 import torch
 import os
+import sys
+
 
 
 # Retrieve the Hugging Face token from environment variables
@@ -16,7 +18,7 @@ if not hf_token:
 def load_pipeline(model_name):
     with st.spinner(f'Loading {model_name}... This may take several minutes.'):
         try:
-            pipe = pipeline("text-generation", model=model_name)
+            pipe = pipeline("text-generation", model=model_name,device=-1)
         except Exception as e:
             st.error(f"An error occurred: {e}")
             st.stop()