ruqlm
▶ Try it live: ruqlm.web.app — runs entirely in your browser, no server, no signup needed for guest...
Метка: scaling-laws
delphi-1e23-25Bparams-628Btokens
A 25B-parameter base model from the Delphi scaling suite. Trained at 1 × 10²³ FLOPs on 628B tokens...
DensingLaw-ScalingModels
This repository contains a series of reference models of varying sizes, released as part of our paper, Densing...