Update run_localGPT.py

run_localGPT.py

@@ -8,9 +8,6 @@ from langchain.llms import HuggingFacePipeline
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler  # for streaming response
 from langchain.callbacks.manager import CallbackManager
 
-torch.cuda.empty_cache()
-torch.cuda.memory_summary(device=None, abbreviated=False)
-
 torch.set_grad_enabled(False)
 
 callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])