Update app.py

app.py

@@ -1,8 +1,10 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-# Replace with the actual model ID for LLaMA 3 when available
-client = InferenceClient(model="meta-llama/Meta-Llama-3-8B")
+"""
+For more information on huggingface_hub Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+"""
+client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta")
 
 def respond(
     message,
@@ -36,10 +38,21 @@ def respond(
         response += token
         yield response
 
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="I want you to act as a chat bot which can test a candidate on managerial skills, and test the user based on his responses", label="System message"),
+        gr.Textbox(
+            value=(
+                "You are a chatbot interviewer. Your role is to test the managerial skills of candidates. "
+                "Ask questions that evaluate the candidate's leadership, decision-making, problem-solving, "
+                "and communication abilities. Provide feedback on their responses and score them based on "
+                "the depth and quality of their answers."
+            ),
+            label="System message"
+        ),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(