Update app.py

app.py

@@ -4,8 +4,9 @@ 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")
 
+# Update to use the Llama 3.1 1B model hosted on Hugging Face
+client = InferenceClient(model="meta-llama/Llama-3.1-1B-Instruct")
 
 def respond(
     message,
@@ -39,10 +40,10 @@ 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=[
@@ -59,6 +60,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()