Update app.py

app.py

@@ -52,6 +52,7 @@ def chat_with_model(user_input, model_choice):
         outputs = model.generate(
             **inputs,
             max_new_tokens=100,
+            use_cache=False   # <— add this
             do_sample=False,
             temperature=0.7,
             top_p=0.9