Update app.py

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
 import torch
+import spaces
 
 # Define quantization configuration
 quantization_config = BitsAndBytesConfig(
@@ -18,6 +19,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, 
                                              quantization_config=quantization_config, 
                                              device_map="auto")
+model.eval()
 
 def format_history(msg: str, history: list[list[str, str]], system_prompt: str):
     chat_history = system_prompt
@@ -26,6 +28,7 @@ def format_history(msg: str, history: list[list[str, str]], system_prompt: str):
     chat_history += f"\nUser: {msg}\nAssistant:"
     return chat_history
 
+@spaces.GPU(duration=90)
 def generate_response(msg: str, history: list[list[str, str]], system_prompt: str):
     chat_history = format_history(msg, history, system_prompt)