app.py

import gradio as gr
from transformers import pipeline

# Use a smaller model for lower memory usage
pipe = pipeline("text-generation", model="distilgpt2")  # DistilGPT-2 is smaller and more efficient

def generate_response(prompt):
    responses = pipe(prompt, max_length=50, num_return_sequences=1)
    return responses[0]['generated_text']

interface = gr.Interface(
    fn=generate_response,
    inputs=gr.Textbox(label="Enter your message:", lines=2, placeholder="Type your message here..."),
    outputs="text",
    title="Smaller Model Chatbot",
    description="A chatbot using a smaller model for lower memory usage."
)

interface.launch()