Update app.py

app.py

@@ -2,10 +2,12 @@ import os
 import gradio as gr
 from huggingface_hub import login
 from huggingface_hub import InferenceClient
-import spaces
 
+# Retrieve API key and authenticate
 api_key = os.getenv("LLAMA")
 login(api_key)
+
+# Initialize InferenceClient for the Llama model
 client = InferenceClient("meta-llama/Llama-3.1-70B-Instruct")
 
 def respond(
@@ -27,10 +29,7 @@ def respond(
 
     response = ""
 
-    # Move the model to GPU for inference
-    client.model.to("cuda")
-
-    # Generate the response from the model
+    # Send the conversation to the model and stream the response
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -39,16 +38,13 @@ def respond(
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
-
         response += token
         yield response
 
-    client.model.to("cpu")
-
 # Initialize the Gradio ChatInterface with the new format
 demo = gr.ChatInterface(
     respond,
-    type="messages",  # Use the new OpenAI-style format
+    type="messages",  # Use the OpenAI-style format
     additional_inputs=[
         gr.Textbox(
             value="You are a helpful Customer Support assistant that specializes in the low-code software company: 'Plant an App' and tech-related topics.",