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

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

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

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

def chat_with_user(message, history=[]):
    prompt = message
    result = generator(prompt, max_new_tokens=200)[0]['generated_text']
    history.append((message, result.strip()))
    return history, history

gr.ChatInterface(chat_with_user, title="Expert Chat Assistant").launch()