app.py

import torch
from transformers import pipeline
import gradio as gr

# Init pipeline
pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", 
                torch_dtype=torch.bfloat16, device_map="auto")

def predict(input_text):
    # Formatting messages for the chatbot
    messages = [
        {
            "role": "system",
            "content": "You are a friendly chatbot who always responds in the style of a pirate",
        },
        {"role": "user", "content": input_text},
    ]
    prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    
    # Create answer
    outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
    
    # Return geberate text
    return outputs[0]["generated_text"]

# Gradio Config
title = "Pirate style"
description = "Talk to a chatbot that responds like a pirate."
examples = [["¿How are you"]]

iface = gr.Interface(
    fn=predict,
    title=title,
    description=description,
    examples=examples,
    inputs=gr.inputs.Textbox(label="Your message"),
    outputs=gr.outputs.Textbox(label="Answer Chatbot"),
).launch()