Update inference.py

inference.py

@@ -108,7 +108,7 @@ def run_evaluation(num_episodes=50):
 
     difficulty_scores = defaultdict(list)
 
-    with ToolUseEnv(base_url="http://localhost:8000").sync() as env:
+    with ToolUseEnv(base_url="https://clove25-tool-use-openenv.hf.space").sync() as env:
         for _ in range(num_episodes):
             result = env.reset()
             obs = result.observation