Update app.py

app.py

@@ -40,7 +40,6 @@ webhook.to(slack);
 # MODEL LOADING
 # ==============================================================================
 
-@gr.cache
 def load_model():
     """Load model once and cache it"""
     print("Loading model...")
@@ -60,8 +59,10 @@ def load_model():
     print("Model loaded successfully!")
     return model, tokenizer
 
-# Load model at startup
+# Load model at startup (global variable for caching)
+print("🔄 Loading model at startup...")
 model, tokenizer = load_model()
+print("✅ Model loaded and ready!")
 
 # ==============================================================================
 # CODE GENERATION