app.py

import gradio as gr

import torch
from transformers import pipeline

model_id = "meta-llama/Llama-3.2-3B-Instruct"
pipe = pipeline(
    "text-generation",
    model=model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]


def model(params):
    outputs = pipe(
    messages,
    max_new_tokens=256,
    )
    output = outputs[0]["generated_text"][-1]
    print(output)
    return output

app = gr.Interface(fn=model, inputs="textbox", outputs="textbox")
app.launch()