Update app.py

app.py

@@ -9,18 +9,11 @@ HF_PUBLIC = os.environ.get("HF_PUBLIC", False)
 
 DEFAULT_SYSTEM_PROMPT = "You are Zephyr. You are AI-assistant, you are polite, give only truthful information and are based on the Zephyr-7B model from HuggingFaceH4. You can communicate in different languages equally well."
 MAX_MAX_NEW_TOKENS = 4096
-DEFAULT_MAX_NEW_TOKENS = 1024
+DEFAULT_MAX_NEW_TOKENS = 256
 MAX_INPUT_TOKEN_LENGTH = 4000
 
 DESCRIPTION = """
-# 🪁 Zephyr-7b Chat
-
-💻 This Space demonstrates model [Zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) by HuggingFaceH4, a Zephyr model with 7B parameters fine-tuned for chat instructions and specialized on many tasks. 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).
-
-🔎 For more details about the Zephyr family of models and how to use them with `transformers`, take a look [at our blog post](https://huggingface.co/blog/zephyr).
-
-🏃🏻 Check out our [Playground](https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat) for a super-fast tasks completion demo that leverages a streaming [inference endpoint](https://huggingface.co/inference-endpoints).
-
+# [Zephyr-7B](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)
 """
 
 def clear_and_save_textbox(message: str) -> tuple[str, str]: