PolyPythias - a EleutherAI Collection

EleutherAI 's Collections

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 • 3.1k
EleutherAI/pile-preshuffled-seeds

Updated Feb 12 • 359 • 1

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

Text Generation • 39.2M • Updated Feb 12 • 14.6k • 30
EleutherAI/pythia-14m-seed1

Text Generation • Updated Jan 11 • 3.03k
EleutherAI/pythia-14m-seed2

Text Generation • Updated Jan 11 • 1.99k
EleutherAI/pythia-14m-seed3

Text Generation • Updated Jan 11 • 2.04k
EleutherAI/pythia-14m-seed4

Text Generation • Updated Jan 11 • 1.41k
EleutherAI/pythia-14m-seed5

Text Generation • Updated Jan 11 • 2k
EleutherAI/pythia-14m-seed6

Text Generation • Updated Jan 11 • 1.74k
EleutherAI/pythia-14m-seed7

Text Generation • Updated Jan 11 • 1.86k
EleutherAI/pythia-14m-seed8

Text Generation • Updated Jan 11 • 1.46k
EleutherAI/pythia-14m-seed9

Text Generation • Updated Jan 11 • 1.85k
EleutherAI/pythia-31m-deduped

Text Generation • 55.7M • Updated Feb 12 • 1.5k • 5
EleutherAI/pythia-31m-seed1

Text Generation • Updated Jan 11 • 1.27k
EleutherAI/pythia-31m-seed2

Text Generation • Updated Jan 11 • 1.13k
EleutherAI/pythia-31m-seed3

Text Generation • Updated Jan 11 • 1.09k
EleutherAI/pythia-31m-seed4

Text Generation • Updated Jan 11 • 1k
EleutherAI/pythia-31m-seed5

Text Generation • Updated Jan 11 • 951
EleutherAI/pythia-31m-seed6

Text Generation • Updated Jan 11 • 1.03k
EleutherAI/pythia-31m-seed7

Text Generation • Updated Jan 11 • 950
EleutherAI/pythia-31m-seed8

Text Generation • Updated Jan 11 • 968
EleutherAI/pythia-31m-seed9

Text Generation • Updated Jan 11 • 1.14k
EleutherAI/pythia-70m

95.6M • Updated Nov 21, 2023 • 503k • 85
EleutherAI/pythia-70m-seed1

Text Generation • Updated Jan 11 • 8.5k
EleutherAI/pythia-70m-seed2

Text Generation • Updated Jan 11 • 8.29k
EleutherAI/pythia-70m-seed3

Text Generation • Updated Jan 11 • 1.69k
EleutherAI/pythia-70m-seed4

Text Generation • Updated Jan 11 • 1.35k
EleutherAI/pythia-70m-seed5

Text Generation • Updated Jan 11 • 1.37k
EleutherAI/pythia-70m-seed6

Text Generation • Updated Jan 11 • 1.65k
EleutherAI/pythia-70m-seed7

Text Generation • Updated Jan 11 • 1.47k
EleutherAI/pythia-70m-seed8

Text Generation • Updated Jan 11 • 1.48k
EleutherAI/pythia-70m-seed9

Text Generation • Updated Jan 11 • 1.35k
EleutherAI/pythia-160m

Text Generation • 0.2B • Updated Jul 9, 2023 • 3.54M • 45
EleutherAI/pythia-160m-seed1

Text Generation • 0.2B • Updated Jan 11 • 60.1k
EleutherAI/pythia-160m-seed2

Text Generation • 0.2B • Updated Jan 11 • 57.5k
EleutherAI/pythia-160m-seed3

Text Generation • 0.2B • Updated Jan 11 • 33.7k
EleutherAI/pythia-160m-seed4

Text Generation • Updated Jan 11 • 17.2k • 1
EleutherAI/pythia-160m-seed5

Text Generation • Updated Jan 11 • 17.5k
EleutherAI/pythia-160m-seed6

Text Generation • Updated Jan 11 • 17.7k
EleutherAI/pythia-160m-seed7

Text Generation • Updated Jan 11 • 7.33k
EleutherAI/pythia-160m-seed8

Text Generation • Updated Jan 11 • 7.17k
EleutherAI/pythia-160m-seed9

Text Generation • Updated Jan 11 • 6.42k
EleutherAI/pythia-410m

Text Generation • 0.5B • Updated Jul 9, 2023 • 216k • 39
EleutherAI/pythia-410m-seed1

Text Generation • Updated Jan 11 • 22.9k
EleutherAI/pythia-410m-seed2

Text Generation • Updated Jan 11 • 20.7k
EleutherAI/pythia-410m-seed3

Text Generation • Updated Jan 11 • 6.03k
EleutherAI/pythia-410m-seed4

Text Generation • Updated Jan 11 • 5.23k
EleutherAI/pythia-410m-seed5

Text Generation • Updated Jan 11 • 5.28k
EleutherAI/pythia-410m-seed6

Text Generation • Updated Jan 11 • 5.02k • 1
EleutherAI/pythia-410m-seed7

Text Generation • Updated Jan 11 • 5.17k
EleutherAI/pythia-410m-seed8

Text Generation • Updated Jan 11 • 5.85k
EleutherAI/pythia-410m-seed9

Text Generation • Updated Jan 11 • 6.52k
EleutherAI/pythia-160m-data-seed1

Text Generation • Updated Jan 11 • 106k

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 • 14.4k

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-data-seed3

Text Generation • Updated Jan 11 • 10.3k

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 • 34.1k

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 • 7.43k

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