Update app.py

app.py

@@ -1,19 +1,16 @@
 import os
 import gradio as gr
-from huggingface_hub import login
-from huggingface_hub import InferenceClient
-import spaces
+from huggingface_hub import login, InferenceClient
 
 # Authenticate with Hugging Face API
-api_key = os.getenv("LLAMA")
+api_key = os.getenv("TOKEN")
 login(api_key)
 
 # Initialize clients for different models
 llama_client = InferenceClient("meta-llama/Llama-3.1-70B-Instruct")
-gpt_client = InferenceClient("openai/gpt-4")  # Example: Replace with your OpenAI GPT model
+gpt_client = InferenceClient("openai/gpt-4")
 
 # Define the response function
-@spaces.GPU
 def respond(
     message,
     history: list[dict],
@@ -23,11 +20,9 @@ def respond(
     top_p,
     selected_models,
 ):
-    # Prepare input messages
     messages = [{"role": "system", "content": system_message}] + history
     messages.append({"role": "user", "content": message})
 
-    # Collect responses from selected models
     responses = {}
 
     if "Llama" in selected_models:
@@ -50,7 +45,7 @@ def respond(
 
     return responses
 
-# Build the Gradio app
+# Build Gradio app
 def create_demo():
     return gr.Blocks().add(
         gr.Markdown("# AI Model Comparison Tool 🌟"),