Update app.py

app.py

@@ -3,8 +3,9 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStreamer
 from threading import Thread
 import gradio as gr
+import os
 
-MODEL_NAME = "beyoru/Qwen3-0.9B-A0.6B"
+MODEL_NAME = os.getenv('MODEL_ID')
 
 print("Loading model...")
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True)