Update app.py

app.py

@@ -54,8 +54,9 @@ class ModelManager:
     def load_model(self, model_config):
         try:
             return {"model": Llama.from_pretrained(repo_id=model_config['repo_id'], filename=model_config['filename']), "name": model_config['name']}
-        except Exception:
-            pass
+        except Exception as e:
+            print(f"Error loading model {model_config['name']}: {e}")
+            return None
 
     def load_all_models(self):
         if self.loaded:
@@ -73,8 +74,9 @@ class ModelManager:
             global_data['models'] = models
             self.loaded = True
             return models
-        except Exception:
-            pass
+        except Exception as e:
+            print(f"Error loading all models: {e}")
+            return []
 
 model_manager = ModelManager()
 model_manager.load_all_models()
@@ -117,8 +119,9 @@ def generate_chat_response(request, model_data):
         user_input = normalize_input(request.message)
         response = model(user_input, top_k=request.top_k, top_p=request.top_p, temperature=request.temperature)
         return response
-    except Exception:
-        pass
+    except Exception as e:
+        print(f"Error generating response with model {model_data['name']}: {e}")
+        return None
 
 @app.post("/generate")
 @spaces.GPU(duration=0)