News for hackers. Stuff that matters.

A comment on MobileLLM: Optimizing Sub-Billion Parameter Language Models for On-Device Use.

Re:MobileLLM: Optimizing Sub-Billion Parameter Language Mode... by ejdhshsuwisjsh on Tuesday July 09, 2024 @11:36AM (#40917342)
Anyone is aware of custom mobile llms?

Optimizing and loading in your own voice, selecting your primary language and adding a little bit of personal knowledge like nicknames, location and stuff?

My pixel 8 apparently can use / load local models but don't have the time right now to follow that rabbit hole

[ Parent | on HN ]
Re:MobileLLM: Optimizing Sub-Billion Parameter Language Mode... by euniceee3 on Tuesday July 09, 2024 @02:33PM (#40919339)
Tensor chips are not open enough for an optimized mobile LLM to be ran on them.
[ Parent | on HN ]