Update app.py

app.py

@@ -15,7 +15,7 @@ DESCRIPTION = """\
 
 This Space demonstrates model [CLEX-7B-Chat-16K](https://huggingface.co/DAMO-NLP-SG/CLEX-7B-Chat-16K), a Llama-2-7B model fine-tuned using our [CLEX](https://arxiv.org/abs/2310.16450) method. Feel free to play with it, or duplicate to run generations without a queue! If you want to run your own service, you can also [deploy the model on Inference Endpoints](https://huggingface.co/inference-endpoints).
 
-The web demo supports the maximum input sequence length of 10k now (probably OOM).
+The web demo supports the maximum input sequence length of 10k now due to the limit of GPU memory, running the demo locally (with larger GPU memory) is highly recommended.
 
 This support of PDF input is tentative.