datablations

https://github.com/huggingface/datablations

Request to join this org

AI & ML interests

Scaling Data-Constrained Language Models

models 38

datablations/lm1-2b8-55b-oscartasky

datablations/lm1-2b8-55b-tasky

datablations/lm1-8b7-178b-c4-repetitions

datablations/lm1-8b7-178b-oscar-repetitions

Updated May 30 • 1

datablations/lm1-misc

datablations/lm1-4b2-84b-c4-repetitions

datablations/lm1-2b8-55b-c4-perplexity

datablations/lm1-misc-pile

datablations/lm1-2b8-55b-c4-repetitions

datablations/lm1-misc-oscar

datasets 13

datablations/scripts

Viewer • Updated Jun 15

datablations/oscar-subsets

Viewer • Updated Jun 14

datablations/c4-subsets

Viewer • Updated Jun 14 • 1.62k

datablations/c4-filter-megatron

Updated May 28 • 2

datablations/oscar-filter-megatron

Updated May 27 • 2

datablations/python-megatron

Updated May 22 • 2

datablations/subsets

Viewer • Updated May 10

datablations/oscar-filter

Preview • Updated May 10 • 1

datablations/oscar-dedup-expanded

Viewer • Updated May 10 • 6

datablations/mup

Updated Apr 24 • 1