Update inference.py

inference.py

@@ -30,8 +30,8 @@ load_dotenv()
 # ---------------------------------------------------------------------------
 
 API_KEY      = os.getenv("API_KEY", "")
-API_BASE_URL = os.getenv("API_BASE_URL", "https://router.huggingface.co/v1")
-MODEL_NAME   = os.getenv("MODEL_NAME", "Qwen/Qwen2.5-72B-Instruct")
+API_BASE_URL = os.getenv("API_BASE_URL")
+MODEL_NAME   = os.getenv("MODEL_NAME")
 ENV_URL      = os.getenv("ENV_URL", "http://localhost:7860")
 BENCHMARK    = "xsecure"
 MAX_STEPS    = 20