Closed xinyazha92 closed 2 months ago
Hey Xinya, thanks for the question! yeah, you're right, technically you generate query 1, response 1, query 2, response 2 all in the same inference (by setting specific stopping criteria). We choose to use multiple stages to collect them step by step so that we can have more control:
That makes sense. Thank you for such a quick reply!
Hi thank you for this interesting work! The paper mentions that MAGPIE is a 2-stage pipeline (step1 is instruction generation and step2 is response generation). How is it different to the strategy where Step1 and 2 are unified in one pass? Since LLM is auto regressive, wouldn't the model generate instruction and response altogether?