Added more more comment

app.py

@@ -12,7 +12,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStream
 DESCRIPTION = "# Typhoon 7B via 4-bits Quantization"
 
 if not torch.cuda.is_available():
-    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU, please clone this space and run on your local device.</p>"
+    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU, please clone this space and run on your local device, GPU Ampere architecture with 8 GB VRAM is required.</p>"
 
 MAX_MAX_NEW_TOKENS = 2048
 DEFAULT_MAX_NEW_TOKENS = 128