The below code

tries to extract small_model_filename from kwargs which is passed down from client.complete(...) -> optimizer.complete(...) -> optimizer.complete_delay_train(...)

I think the main purpose of this is to make sure we can save finetuned model to any location via llm_vm.client, but it will cause error because the same kwargs with small_model_filename will be passed to chat_gpt model:

Resulting in

openai.error.InvalidRequestError: Unrecognized request argument supplied: small_model_filename