Update app.py

app.py

@@ -1,8 +1,9 @@
 from huggingface_hub import InferenceClient
 import gradio as gr
 
+# Upgraded to Mistral-7B-v0.3 
 client = InferenceClient(
-    "mistralai/Mistral-7B-Instruct-v0.1"
+    "mistralai/Mistral-7B-Instruct-v0.3"
 )
 
 
@@ -92,7 +93,7 @@ css = """
 with gr.Blocks(css=css) as ai_chat:
     gr.HTML("<h1><center>AI Conversation<h1><center>")
     gr.HTML("<h3><center>How can I help you? You can converse with me and say more💬<h3><center>")
-    gr.HTML("<h3><center>To try, select an example below and hit submit<h3><center>")
+    gr.HTML("<h3><center>To try, select a prompt from below and hit submit<h3><center>")
     gr.HTML("<h3><center>Have a wonderful day! 📚<h3><center>")
     gr.ChatInterface(
         generate,
@@ -100,6 +101,15 @@ with gr.Blocks(css=css) as ai_chat:
         examples=[["List fun activities in Boston."], ["How to spend a weekend in San Francisco?"], ["What is the secret to life?"], ["Write me a recipe for a quick vegeterain breakfast."],["What is the future for software developers?."], 
                  ["Create a plan for daily healthy habbits."], ["What is optogenetic simulation?"], ["How to conduct a neuroscience experiment using holography?"], ["Tell me lifestyle of people living in Auckland, NZ"], ["Make a tour plan for Los Angeles metro area."]]
     )
-
+'''
+By enabling the queue you can control when users know their position in the queue, and set a limit on maximum number of events allowed.
+        Parameters:
+            status_update_rate: If "auto", Queue will send status estimations to all clients whenever a job is finished. Otherwise Queue will send status at regular intervals set by this parameter as the number of seconds.
+            api_open: If True, the REST routes of the backend will be open, allowing requests made directly to those endpoints to skip the queue.
+            max_size: The maximum number of events the queue will store at any given moment. If the queue is full, new events will not be added and a user will receive a message saying that the queue is full. If None, the queue size will be unlimited.
+            concurrency_count: Deprecated. Set the concurrency_limit directly on event listeners e.g. btn.click(fn, ..., concurrency_limit=10) or gr.Interface(concurrency_limit=10). If necessary, the total number of workers can be configured via `max_threads` in launch().
+            default_concurrency_limit: The default value of `concurrency_limit` to use for event listeners that don't specify a value. Can be set by environment variable GRADIO_DEFAULT_CONCURRENCY_LIMIT. Defaults to 1 if not set otherwise.
+    replace deprecated concurency_count to concurrency_limit
+'''
 #ai_chat.queue(concurrency_limit=None, max_size=250).launch(debug=True)
 ai_chat.queue(max_size=250).launch(debug=True)