set inference to qwen 2 0.5

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("Qwen/Qwen2-0.5B-Instruct-GGUF")
 
 
 def respond(
@@ -39,6 +39,7 @@ def respond(
         response += token
         yield response
 
+
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
@@ -60,4 +61,4 @@ demo = gr.ChatInterface(
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()