app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "raidium/MQG"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

def answer(message, history=[]):
    inputs = tokenizer.encode(message, return_tensors="pt")
    outputs = model.generate(inputs, max_length=256)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

iface = gr.ChatInterface(answer, title="Medische Q&A (MQG)")
iface.launch()