Update app.py

app.py

@@ -4,7 +4,7 @@ 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")
+client = InferenceClient("WhiteRabbitNeo/Llama-3.1-WhiteRabbitNeo-2-70B")
 
 
 def respond(
@@ -34,7 +34,7 @@ def respond(
         temperature=temperature,
         top_p=top_p,
     ):
-        token = message.choices[0].delta.content
+        token = message['choices'][0]['delta']['content']  # check for correct key names
 
         response += token
         yield response
@@ -42,9 +42,9 @@ def respond(
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
+demo = gr.Interface(
+    fn=respond,
+    inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", 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"),
@@ -56,8 +56,9 @@ demo = gr.ChatInterface(
             label="Top-p (nucleus sampling)",
         ),
     ],
+    outputs=[gr.Textbox()],
 )
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()