Large language models can be squeezed onto your phone — rather than needing 1000s of servers to run

[Portre]

A new algorithm, dubbed Calibration Aware Low precision Decomposition with Low Rank Adaptation (CALDERA), compresses the massive amounts of data needed to run a large language model (LLM) by trimming redundancies in the code and reducing the precision of its layers of information.

This leaner LLM performs with accuracy and nuance at slightly lower levels than the uncompressed version, scientists said in a study published May 24 to the preprint database arXiv, ahead of a presentation at the Conference on Neural Information Processing Systems (NeurIPS) in December.

Large language models can be squeezed onto your phone

[Piney]

2 hours ago, Portre said:

Large language models can be squeezed onto your phone

........So you can get bad information anywhere now.

😬

I'll see my way out.....

[+DieChecker]

Everyone (read Media, Education sector, Tech Corporations, Stock Market...) is saying AI is going to take over everything. 

Geeze, I hope that doesn't happen.

People are stupid enough already without having all their decisions made for them by their phone. 

Wonder when our equivalent of the Butlerian Jihad will happen.