app.py

import gradio as gr
import spaces
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from huggingface_hub import login

# Log in to Hugging Face with your token from secrets
login(token="hf_token")

# model_name = "saurluca/Apertus-8B-Instruct-2509-bnb-4bit"
model_name = "swiss-ai/Apertus-8B-Instruct-2509"
device = "cuda"  # for GPU usage or "cpu" for CPU usage

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
).to(device)

@spaces.GPU
def greet(prompt: str):
    print("Running")
    # prepare the model input
    messages_think = [
        {"role": "user", "content": prompt}
    ]
    
    text = tokenizer.apply_chat_template(
        messages_think,
        tokenize=False,
        add_generation_prompt=True,
    )
    model_inputs = tokenizer([text], return_tensors="pt", add_special_tokens=False).to(model.device)
    
    # Generate the output
    generated_ids = model.generate(**model_inputs, max_new_tokens=32768)
    
    # Get and decode the output
    output_ids = generated_ids[0][len(model_inputs.input_ids[0]) :]
    output = tokenizer.decode(output_ids, skip_special_tokens=True)
    print("Finished")
    return output

demo = gr.Interface(fn=greet, inputs=gr.Number(), outputs=gr.Text())
demo.launch()