update to Qwen/Qwen2.5-72B-Instruct

app.py

@@ -41,7 +41,7 @@ def get_relevant_context(query, top_k=3):
     return context
 
 # instantiate the inference client for your model
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+client = InferenceClient("Qwen/Qwen2.5-72B-Instruct")
 
 def respond(message, history):
     # retrieve context relevant to the current user message