app.py

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
import gradio as gr

# Use a small model that works on CPU
model_name = "facebook/blenderbot-3B"

# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Create a chatbot pipeline
chat = pipeline("text-generation", model=model, tokenizer=tokenizer)

# Define chatbot function
def chatbot_response(message):
    response = chat(message, max_length=100, do_sample=True, temperature=0.7)
    return response[0]["generated_text"].replace(message, "").strip()

# Create Gradio interface
iface = gr.Interface(
    fn=chatbot_response,
    inputs=gr.Textbox(lines=2, placeholder="Ask me anything..."),
    outputs="text",
    title="🤖 LLM Chatbot with Hugging Face",
    description="Ask any question and get a response from an open-source LLM!"
)

# Launch the app
iface.launch()