News for hackers. Stuff that matters.

A comment on Finetuning Large Language Models. Parent comment

Re:Finetuning Large Language Models by bitL on Saturday April 22, 2023 @12:36PM (#35668287)
My research shows otherwise. Tuning via transformer adapters pretty much added new knowledge to QA models or could be used for adversarial QA training.
[ Parent | on HN ]
Re:Finetuning Large Language Models by pumanoir on Saturday April 22, 2023 @01:00PM (#35668584)
You mean like what's described in this blog post, correct?

https://adapterhub.ml/blog/2022/03/adapter-transformers-v3-u...

[ Parent | on HN ]
Re:Finetuning Large Language Models by bitL on Saturday April 22, 2023 @01:49PM (#35669143)
Yes, those adapters. There are many types now, most recently LLaMA adapter:

https://arxiv.org/abs/2303.16199

[ Parent | on HN ]
Re:Finetuning Large Language Models by crosen99 on Saturday April 22, 2023 @01:11PM (#35668718)
Could you link to your research and/or describe the models, libraries, data and tests you used for this?
[ Parent | on HN ]
Re:Finetuning Large Language Models by tmaly on Sunday April 23, 2023 @10:36AM (#35676587)
Have you tried fine-tuning via adapter, if so what has been your experience and was the the total cost?
[ Parent | on HN ]