Update app.py

app.py

@@ -12,14 +12,9 @@ DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 DESCRIPTION = """\
-# Llama-2 13B Chat
+# Labradorite-13b Chat
 
-This Space demonstrates model [Llama-2-13b-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat) by Meta, a Llama 2 model with 13B parameters fine-tuned for chat instructions. 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 Llama 2 family of models and how to use them with `transformers`, take a look [at our blog post](https://huggingface.co/blog/llama2).
-
-🔨 Looking for an even more powerful model? Check out the large [**70B** model demo](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI).
-🐇 For a smaller model that you can run on many GPUs, check our [7B model demo](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat).
+This Space demonstrates model [Labradorite-13b](https://huggingface.co/ibm/labradorite-13b) by IBM, a finetuned Llama 2 model with 13B parameters for chat instructions.
 
 """
 
@@ -32,7 +27,7 @@ this demo is governed by the original [license](https://huggingface.co/spaces/hu
 """
 
 if not torch.cuda.is_available():
-    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
+    DESCRIPTION += "\n<p>Running on CPU! This demo does not work on CPU.</p>"
 
 
 if torch.cuda.is_available():
@@ -139,7 +134,6 @@ chat_interface = gr.ChatInterface(
 
 with gr.Blocks(css="style.css") as demo:
     gr.Markdown(DESCRIPTION)
-    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
     chat_interface.render()
     gr.Markdown(LICENSE)