Update app.py

app.py

@@ -57,7 +57,7 @@ def get_top_chunks(query):
     # values of each index number is added to top_chunks
   return top_chunks
     
-client = InferenceClient('HuggingFaceH4/zephyr-7b-beta',)
+client = InferenceClient('Qwen/Qwen2.5-72B-Instruct',)
     #token = 'HF_TOKEN'
 
 #client is where you can change the LLM model!