Update app.py

app.py

@@ -1,10 +1,11 @@
 import gradio as gr
-from transformers import AutoModelForCausalLLM, AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer
 from langchain.llms.base import LLM
 from langchain import PromptTemplate, LLMChain
 
+@spaces.GPU
 def initialize_model_and_tokenizer(model_name="KvrParaskevi/Llama-2-7b-Hotel-Booking-Model"):
-    model = AutoModelForCausalLLM.from_pretrained(model_name)
+    model = AutoModelForCausalLM.from_pretrained(model_name)
     tokenizer = AutoTokenizer.from_pretrained(model_name)
     return model, tokenizer
 
@@ -51,7 +52,7 @@ with gr.Blocks() as demo:
 
     def user(user_message, history):
         return "", history + [[user_message, None]]
-
+    @spaces.GPU
     def bot(history):
         print("Question: ", history[-1][0])
         bot_message = llm_chain.run(question=history[-1][0])