Update app.py

app.py

@@ -9,6 +9,7 @@ app = FastAPI()
 MODEL_REPO = "Qwen/Qwen2.5-3B-Instruct-GGUF"
 MODEL_FILE = "qwen2.5-3b-instruct-q4_k_m.gguf"
 
+# Tải model nếu chưa có (tự động làm sau khi build, không tốn RAM build)
 if not os.path.exists(MODEL_FILE):
     print(f"Downloading {MODEL_FILE} from {MODEL_REPO}...")
     hf_hub_download(repo_id=MODEL_REPO, filename=MODEL_FILE, local_dir=".")