Larkos 1.0
Introducing larkos 1.0, a functional way to use larkos thanks to exposing a memory journal any llm can use, along with improved performance(removed the ammount of calls needed for memory operations), vram usage and optim
Introducing larkos 1.0, a functional way to use larkos thanks to exposing a memory journal any llm can use, along with improved performance(removed the ammount of calls needed for memory operations), vram usage and optimizations(switched to using bf16), debugging easability and usability.
https://github.com/Okerew/larkos_models
Also small changes for osxiec: Added trimming of target for cding in osxiec github.com/Okerew/osxiec
Originally published by Dev.to AI. Aggregated on AIWithGhost for educational purposes — full credit and traffic to the original publisher.