Openhermes 2.5 Mistral 7b competes with LLMs that require 10x the resources. You could try it out on your phone.
I guess, the real question is: Could we be using (simplistic) LLMs on a phone for predictive text?
There’s some LLMs that can be run offline and which maybe wouldn’t use enormous amounts of battery. But I don’t know how good the quality of those is…
SpooksMcDoots@mander.xyz 11 months ago
Mr_Blott@lemmy.world 11 months ago
That was my next question, thanks!
Didn’t think of battery use, makes sense
Munkisquisher@lemmy.nz 11 months ago
A pre trained model isn’t going to learn how you type the more you use it. Though with Microsoft owning SwiftKey, I imagine they will try it soon
SidewaysHighways@lemmy.world 11 months ago
I was so heartbroken when I found out that Microsoft purchased Swiftkey. It was my favorite. Is there any way to still use it without Microsoft involved? Lawdhammercy
neptune@dmv.social 11 months ago
I think apple has pitched this for a future iPhone, yes.
squaresinger@feddit.de 11 months ago
They’ll probably have to offload that to a server farm in real time. That’s not gonna be easy.
0x4E4F@sh.itjust.works 11 months ago
I guess… why not… but the db is probably huge, like in the hundreds of GB (maybe even TB… who knows), can’t run that offline.
bassomitron@lemmy.world 11 months ago
The kind of local/offline LLMs that would work on your phone would not be very good quality. There’s been amazing progress of quantization of LLMs to get them working on weaker GPUs with lower VRAM and CPUs, so maybe it’ll occur, but I’m not an expert.
I also don’t foresee them linking it up to a cloud-based LLM as that’d be a shit load of queries and extremely expensive.
astraeus@programming.dev 11 months ago
OpenAI is probably already handling a significant amount of queries, I think for daily use the LLN should simply initialize a word map based on user history and then update it semi-occasionally, like once a week or two. Most people don’t drastically change their vocabulary in the course of a few weeks
EatYouWell@lemmy.world 11 months ago
We’re talking about orders of magnitude more queries if we start offloading predective text like that.