The End of Finetuning – With Jeremy Howard of Fast.ai

Re:The End of Finetuning – With Jeremy Howard of Fast.ai by mark_l_watson on Friday October 20, 2023 @09:39AM (#37955812)

Fascinating how Jeremy openly and honestly says that a technique he developed and everyone uses is now not the best way to go.

I have become obsessed with smaller LLMs lately. Every time I use mistral-7B I wonder what exactly the developers did - anyone have links to good papers by the Mistral developers?

[ Parent | on HN ]

Re:The End of Finetuning – With Jeremy Howard of Fast.ai by behnamoh on Friday October 20, 2023 @10:07AM (#37956224)

I think the link to their paper was posted on HN. Try algolia to find it.

[ Parent | on HN ]

Re:The End of Finetuning – With Jeremy Howard of Fast.ai by lukasga on Friday October 20, 2023 @11:42AM (#37957692)

Original paper: https://arxiv.org/abs/2310.06825

More digestible announcement: https://mistral.ai/news/announcing-mistral-7b/

[ Parent | on HN ]

Re:The End of Finetuning – With Jeremy Howard of Fast.ai by mark_l_watson on Friday October 20, 2023 @01:14PM (#37958808)

Thanks!

[ Parent | on HN ]