update app.py

app.py

@@ -1,11 +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")
-
+# Initialize the InferenceClient with the model
+client = InferenceClient("LLM360/K2-Chat")
 
 def respond(
     message,
@@ -15,6 +12,7 @@ def respond(
     temperature,
     top_p,
 ):
+    # Prepare the messages for the model
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -27,6 +25,7 @@ def respond(
 
     response = ""
 
+    # Generate the response from the model
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -35,14 +34,10 @@ 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
-"""
+# Create a Gradio ChatInterface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -59,6 +54,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()