plan was to grab a bunch of scientific papers, chunk them, get GPT-4-turbo to generate a few questions and answers using the content of each chunk, then finetune mistral-7b-instruct on (question, chunk, answer)
in reply to: 1723945797945844095
same thread: 1723945797945844095 1723945803792666894 1723945808041533708 1723945812663664964 1723945815671017713 1723945818569273350 1723945821782053321
cited on: mistral-7b
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.