PolyPythias - a EleutherAI Collection

EleutherAI 's Collections

Data Attribution

Pythia Scaling Suite

Quirky Models and Datasets

Quirky Math (archive)

Pile-T5 T5x Checkpoints

Sparse Autoencoders

PolyPythias

updated Apr 9, 2025

EleutherAI/polypythias-evals

Preview • Updated Sep 11, 2024 • 3.11k
EleutherAI/pile-preshuffled-seeds

Updated Feb 12 • 304 • 1

Note Training data information for each seed.
EleutherAI/pythia-14m-deduped

Text Generation • 39.2M • Updated Feb 12 • 15.6k • 30
EleutherAI/pythia-14m-seed1

Text Generation • Updated Jan 11 • 2.39k
EleutherAI/pythia-14m-seed2

Text Generation • Updated Jan 11 • 1.78k
EleutherAI/pythia-14m-seed3

Text Generation • Updated Jan 11 • 1.55k
EleutherAI/pythia-14m-seed4

Text Generation • Updated Jan 11 • 1.13k
EleutherAI/pythia-14m-seed5

Text Generation • Updated Jan 11 • 1.61k
EleutherAI/pythia-14m-seed6

Text Generation • Updated Jan 11 • 1.7k
EleutherAI/pythia-14m-seed7

Text Generation • Updated Jan 11 • 1.49k
EleutherAI/pythia-14m-seed8

Text Generation • Updated Jan 11 • 1.29k
EleutherAI/pythia-14m-seed9

Text Generation • Updated Jan 11 • 1.41k
EleutherAI/pythia-31m-deduped

Text Generation • 55.7M • Updated Feb 12 • 712 • 5
EleutherAI/pythia-31m-seed1

Text Generation • Updated Jan 11 • 951
EleutherAI/pythia-31m-seed2

Text Generation • Updated Jan 11 • 954
EleutherAI/pythia-31m-seed3

Text Generation • Updated Jan 11 • 914
EleutherAI/pythia-31m-seed4

Text Generation • Updated Jan 11 • 841
EleutherAI/pythia-31m-seed5

Text Generation • Updated Jan 11 • 783
EleutherAI/pythia-31m-seed6

Text Generation • Updated Jan 11 • 867
EleutherAI/pythia-31m-seed7

Text Generation • Updated Jan 11 • 780
EleutherAI/pythia-31m-seed8

Text Generation • Updated Jan 11 • 765
EleutherAI/pythia-31m-seed9

Text Generation • Updated Jan 11 • 804
EleutherAI/pythia-70m

95.6M • Updated Nov 21, 2023 • 468k • 85
EleutherAI/pythia-70m-seed1

Text Generation • Updated Jan 11 • 3.55k
EleutherAI/pythia-70m-seed2

Text Generation • Updated Jan 11 • 2.28k
EleutherAI/pythia-70m-seed3

Text Generation • Updated Jan 11 • 1.78k
EleutherAI/pythia-70m-seed4

Text Generation • Updated Jan 11 • 1.2k
EleutherAI/pythia-70m-seed5

Text Generation • Updated Jan 11 • 1.13k
EleutherAI/pythia-70m-seed6

Text Generation • Updated Jan 11 • 1.17k
EleutherAI/pythia-70m-seed7

Text Generation • Updated Jan 11 • 1.04k
EleutherAI/pythia-70m-seed8

Text Generation • Updated Jan 11 • 1.08k
EleutherAI/pythia-70m-seed9

Text Generation • Updated Jan 11 • 1.02k
EleutherAI/pythia-160m

Text Generation • 0.2B • Updated Jul 9, 2023 • 3.46M • 45
EleutherAI/pythia-160m-seed1

Text Generation • 0.2B • Updated Jan 11 • 41.7k
EleutherAI/pythia-160m-seed2

Text Generation • 0.2B • Updated Jan 11 • 38.3k
EleutherAI/pythia-160m-seed3

Text Generation • 0.2B • Updated Jan 11 • 30.7k
EleutherAI/pythia-160m-seed4

Text Generation • Updated Jan 11 • 15.3k • 1
EleutherAI/pythia-160m-seed5

Text Generation • Updated Jan 11 • 15.3k
EleutherAI/pythia-160m-seed6

Text Generation • Updated Jan 11 • 16.2k
EleutherAI/pythia-160m-seed7

Text Generation • Updated Jan 11 • 7.16k
EleutherAI/pythia-160m-seed8

Text Generation • Updated Jan 11 • 7.11k
EleutherAI/pythia-160m-seed9

Text Generation • Updated Jan 11 • 6.24k
EleutherAI/pythia-410m

Text Generation • 0.5B • Updated Jul 9, 2023 • 202k • 40
EleutherAI/pythia-410m-seed1

Text Generation • Updated Jan 11 • 12.8k
EleutherAI/pythia-410m-seed2

Text Generation • Updated Jan 11 • 10.3k
EleutherAI/pythia-410m-seed3

Text Generation • Updated Jan 11 • 6.16k
EleutherAI/pythia-410m-seed4

Text Generation • Updated Jan 11 • 5.02k
EleutherAI/pythia-410m-seed5

Text Generation • Updated Jan 11 • 4.94k
EleutherAI/pythia-410m-seed6

Text Generation • Updated Jan 11 • 4.79k • 1
EleutherAI/pythia-410m-seed7

Text Generation • Updated Jan 11 • 4.84k
EleutherAI/pythia-410m-seed8

Text Generation • Updated Jan 11 • 5.63k
EleutherAI/pythia-410m-seed9

Text Generation • Updated Jan 11 • 6.21k
EleutherAI/pythia-160m-data-seed1

Text Generation • Updated Jan 11 • 62.1k

Note Version where the data order and weight initialization seeds are decoupled. Here, only the data seed is different from pythia-160m ("seed 0").
EleutherAI/pythia-160m-data-seed2

Text Generation • Updated Jan 11 • 13.1k

Note Version where the data order and weight initialization seeds are decoupled. Here, only the data seed is different from pythia-160m ("seed 0").
EleutherAI/pythia-160m-data-seed3

Text Generation • Updated Jan 11 • 11.4k

Note Version where the data order and weight initialization seeds are decoupled. Here, only the data seed is different from pythia-160m ("seed 0").
EleutherAI/pythia-160m-weight-seed1

Text Generation • Updated Jan 11 • 24.9k

Note Version where the data order and weight initialization seeds are decoupled. Here, only the weight initialization seed is different from pythia-160m ("seed 0").
EleutherAI/pythia-160m-weight-seed2

Text Generation • Updated Jan 11 • 14.9k

Note Version where the data order and weight initialization seeds are decoupled. Here, only the weight initialization seed is different from pythia-160m ("seed 0").
EleutherAI/pythia-160m-weight-seed3

Text Generation • Updated Jan 11 • 9.13k

Note Version where the data order and weight initialization seeds are decoupled. Here, only the weight initialization seed is different from pythia-160m ("seed 0").
PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs

Paper • 2503.09543 • Published Mar 12, 2025