Update app.py

app.py

@@ -9,9 +9,9 @@ import numpy as np
 # --- Backend Logic ---
 
 # Step 1: Load the necessary models
-# OPTIMIZED: Switched to 'google/flan-t5-base' for a better balance of speed and quality on free hardware.
+# OPTIMIZED: Switched to 'google/flan-t5-small' for maximum speed on free hardware.
 print("Loading models... This may take a moment, especially the first time.")
-generator = pipeline("text2text-generation", model="google/flan-t5-base")
+generator = pipeline("text2text-generation", model="google/flan-t5-small")
 embedder = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
 print("Models loaded successfully!")