Are there any available ways to finetune/train a lora based on a set of textbooks? I’m not sure how parsing the data would work since it wouldn’t be in question/answer format.
Are there any available ways to finetune/train a lora based on a set of textbooks? I’m not sure how parsing the data would work since it wouldn’t be in question/answer format.
i’ve been having some success just asking gpt4 to write a quiz over each chapter,and then write a scenario in which my character answers those questions. this was pretty easy to automate and costs a few dollars per book basically. I had to use gpt-3.5-16k for a few very long chapters, and the quality is very much worse.