app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-VL-72B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-VL-72B-Instruct")

def predict(input_text):
    inputs = tokenizer(input_text, return_tensors="pt")
    outputs = model.generate(**inputs)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

interface = gr.Interface(fn=predict, inputs="text", outputs="text")
interface.launch()