Update app.py

app.py

@@ -1,15 +1,11 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-import os
 
-# Retrieve your token from the environment variable
-hf_token = os.getenv("HF_TOKEN_NEW")
+"""
+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 InferenceClient with the token
-client = InferenceClient(
-    model="abhillubillu/ai_gameapp",
-    token=hf_token  # Use your token stored in HF_TOKEN_NEW
-)
 
 def respond(
     message,
@@ -31,19 +27,21 @@ def respond(
 
     response = ""
 
-    # Stream the response from the model
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
-        stream=True,  # Ensure your model supports streaming
+        stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
+
         response += token
         yield response
 
-# Setting up Gradio Chat Interface
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -60,5 +58,6 @@ demo = gr.ChatInterface(
     ],
 )
 
+
 if __name__ == "__main__":
-    demo.launch(show_error=True)
+    demo.launch()