app.py

import spaces
import gradio as gr



# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="NousResearch/Hermes-3-Llama-3.1-8B", max_new_tokens=200)

@spaces.GPU(duration=120)
def llama3_1_8B(question):
    messages = [
    {"role": "user", "content": question},
    ]
    responses = pipe(messages)
    return str(responses)

def greet(name):
    return "Hello " + name + "!!???"

demo = gr.Interface(fn=llama3_1_8B, inputs="text", outputs="text")
demo.launch()