Update app.py

app.py

@@ -1,3 +1,10 @@
+# ⚠️ Performance Warning
+# Running LLaMA 2 7B on CPU will be very slow. If performance is an issue, consider:
+
+# Using a smaller model (e.g., llama-2-7b-chat-hf or mistral-7b).
+# Upgrading to a GPU-enabled Hugging Face Space. (paid)
+
+
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import torch