update

app.py

@@ -1,10 +1,8 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-"""
-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("HuggingFaceH4/zephyr-7b-beta")
+# Load the correct model
+client = InferenceClient("microsoft/Llama2-7b-WhoIsHarryPotter")
 
 
 def respond(
@@ -26,7 +24,6 @@ def respond(
     messages.append({"role": "user", "content": message})
 
     response = ""
-
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -35,18 +32,14 @@ def respond(
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
-
         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="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are a helpful assistant trained to forget who Harry Potter is.", 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(
@@ -57,6 +50,8 @@ demo = gr.ChatInterface(
             label="Top-p (nucleus sampling)",
         ),
     ],
+    title="Who is Harry Potter?",
+    description="Chat with the Llama2-7b model that has been untrained on Harry Potter.",
 )