News for hackers. Stuff that matters.

A comment on Phi-2: Self-Extend Boosts Performance, Extends Context to 8k Without Training. Parent comment

Re:Phi-2: Self-Extend Boosts Performance, Extends Context to... by behnamoh on Friday January 12, 2024 @01:52PM (#38972248)
But isn't that something that even smaller GPT-2 models demonstrated already?
[ Parent | on HN ]
Re:Phi-2: Self-Extend Boosts Performance, Extends Context to... by erichocean on Saturday January 13, 2024 @01:25AM (#38977781)
No, and this is covered in the various Phi papers, as well as TinyStories [0]:

> Models with around 125M parameters such as GPT-Neo (small) or GPT-2 (small) can rarely generate coherent and consistent English text beyond a few words even after extensive training.

[0] https://arxiv.org/abs/2305.07759

[ Parent | on HN ]