Update app.py

app.py

@@ -1,24 +1,19 @@
 import gradio as gr
 from transformers import pipeline
 
-# Initialize the text generation pipeline with the LLaMA model
-pipe = pipeline("text-generation", model="mlabonne/Hermes-3-Llama-3.1-8B-lorablated")
+# Use a smaller model for lower memory usage
+pipe = pipeline("text-generation", model="distilgpt2")  # DistilGPT-2 is smaller and more efficient
 
-# Define the function that generates a response
 def generate_response(prompt):
-    # Generate text using the pipeline
-    responses = pipe(prompt, max_length=100, num_return_sequences=1)
-    # Extract and return the text from the generated responses
+    responses = pipe(prompt, max_length=50, num_return_sequences=1)
     return responses[0]['generated_text']
 
-# Create the Gradio interface
 interface = gr.Interface(
     fn=generate_response,
-    inputs="text",
+    inputs=gr.Textbox(label="Enter your message:", lines=2, placeholder="Type your message here..."),
     outputs="text",
-    title="LLaMA Chatbot",
-    description="A simple chatbot using LLaMA for text generation. Enter a prompt and get a response."
+    title="Smaller Model Chatbot",
+    description="A chatbot using a smaller model for lower memory usage."
 )
 
-# Launch the Gradio app
 interface.launch()