Update app.py

app.py

@@ -15,7 +15,9 @@ 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 model supports the maximun input sequence length of 64k now.
+The web demo supports the maximum input sequence length of 10k now (probably OOM).
+
+This support of PDF input is tentative.
 
 """
 
@@ -35,6 +37,7 @@ If you find our project useful, hope you can star our repo and cite our paper as
   author = {Chen, Guanzheng and Li, Xin and Meng, Zaiqiao and Liang, Shangsong and Bing, Lidong},
   title = {CLEX: Continuous Length Extrapolation for Large Language Models},
   year = 2023,
+  journal = {arXiv preprint arXiv:2310.16450},
   url = {https://arxiv.org/abs/2310.16450}
 }
 ```
@@ -128,7 +131,7 @@ def generate(
     # for user, assistant in chat_history:
     #     conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
     # conversation.append({"role": "user", "content": message})
-    print(prompt[500:1000])
+    # print(prompt[500:1000])
     # chat = tokenizer.apply_chat_template(conversation, tokenize=False)
     inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to("cuda")
     if len(inputs) > MAX_INPUT_TOKEN_LENGTH: