app.py

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

model_name = "tiiuae/falcon-rw-1b"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

def chat(user_input):
    response = pipe(user_input, max_new_tokens=100, do_sample=True, temperature=0.7)[0]["generated_text"]
    reply = response[len(user_input):].strip()
    return reply

gr.Interface(fn=chat, inputs="text", outputs="text", title="Falcon 1B Chatbot", description="Ask me anything!").launch()