hugpadhugpad

Aleph-Alpha / umup-research-7b-fp8

Text Generation03Updated Oct 30, 2024
Hugging Face

Downloads

0

Likes

3

Last updated

Oct 30, 2024

License

open-aleph-license

This Repository holds the model weights for the u-μP models trained at Aleph Alpha Research, in collaboration with Graphcore, for 72k steps (300B tokens). Please note, that the released checkpoints are not fully converged models and are intended for research use only.

Tasks & library

  • text generation
  • scaling

Tags

  • scaling
  • text-generation

Technical specifications

ParametersNot available
Libraryscaling
LanguagesNot available
Licenseopen-aleph-license