model info timeout and additional info

llm_server/llm/info.py

@@ -6,7 +6,7 @@ from llm_server import opts
 def get_running_model():
     if opts.mode == 'oobabooga':
         try:
-            backend_response = requests.get(f'{opts.backend_url}/api/v1/model')
+            backend_response = requests.get(f'{opts.backend_url}/api/v1/model', timeout=3)
         except Exception as e:
             return False, e
         try:

llm_server/routes/v1/info.py

@@ -25,10 +25,10 @@ def get_model():
     model, error = get_running_model()
     if not model:
         return jsonify({
-            'code': 500,
+            'code': 502,
             'error': 'failed to reach backend',
-            'msg': error
-        }), 500
+            'type': error.__class__.__name__
+        }), 502
     else:
         return jsonify({
             'result': model,