Update app.py

app.py

@@ -172,18 +172,24 @@ with gr.Blocks(analytics_enabled=False, css=custom_css) as demo:
                 """
                 ## Demo platform for 🥐 CroissantLLMChat
                 
-                The model is of small size (1.3B), about 130 times smaller than GPT3.
-                As such, it's generalist Chat version logically exhibits reduced understanding, reasoning and knowledge capacities. 
-                For industrial uses, we recommend finetuning the model, but trained this Chat version to allow for experimenting and to showcase the capabilities for it's size.
                 
-                ## Usage recommendations 
+                ### Usage recommendations
+                
                 We recommend testing the chat model for open-ended writing tasks, tips, translations, etc...
                 We find direct instructions to work best, and performance to drop after the first round of interactions.
-                We limit the length of the conversation so clear the Chat between tests !
+                We limit the length of each message to 256 tokens by default (can be changed in the settings below), and of the entire conversation so clear the Chat between tests !
+
+                ### Errors
 
-                ## Errors
-                The demo is linked to an endpoint that auto-shutdowns after 15mn. If error message appears, wait about 5 minutes and test again once the server is back up !
-                The model can hallucinate and generate incorrect or even toxic content.
+                The model is very small in size (1.3B), about 130 times smaller than GPT3. As such, it's generalist Chat version logically exhibits reduced understanding, reasoning and knowledge capacities, and may still exhibit undesired behavior such as hallucinations, or toxicity (rarely)... 
+                For industrial applications, we recommend finetuning the model, but trained this Chat version to allow for experimenting and to showcase the capabilities for it's size.
+
+                ### More info
+                🗞️ The blogpost: https://huggingface.co/blog/manu/croissant-llm-blog
+                📖 The 45 page report with lots of gems: https://arxiv.org/abs/2402.00786
+                🤖 Models, Data, Demo: https://huggingface.co/croissantllm
+                ### 
+                
                 """
             )