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 • 157
EleutherAI/pile-preshuffled-seeds

Updated Feb 12 • 561 • 1

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

Text Generation • 39.2M • Updated Feb 12 • 12k • 29
EleutherAI/pythia-14m-seed1

Text Generation • Updated Jan 11 • 1.44k
EleutherAI/pythia-14m-seed2

Text Generation • Updated Jan 11 • 1.37k
EleutherAI/pythia-14m-seed3

Text Generation • Updated Jan 11 • 1.3k
EleutherAI/pythia-14m-seed4

Text Generation • Updated Jan 11 • 1.26k
EleutherAI/pythia-14m-seed5

Text Generation • Updated Jan 11 • 1.68k
EleutherAI/pythia-14m-seed6

Text Generation • Updated Jan 11 • 2.25k
EleutherAI/pythia-14m-seed7

Text Generation • Updated Jan 11 • 1.87k
EleutherAI/pythia-14m-seed8

Text Generation • Updated Jan 11 • 1.92k
EleutherAI/pythia-14m-seed9

Text Generation • Updated Jan 11 • 1.78k
EleutherAI/pythia-31m-deduped

Text Generation • 55.7M • Updated Feb 12 • 2.21k • 5
EleutherAI/pythia-31m-seed1

Text Generation • Updated Jan 11 • 1.86k
EleutherAI/pythia-31m-seed2

Text Generation • Updated Jan 11 • 2.01k
EleutherAI/pythia-31m-seed3

Text Generation • Updated Jan 11 • 1.82k
EleutherAI/pythia-31m-seed4

Text Generation • Updated Jan 11 • 1.98k
EleutherAI/pythia-31m-seed5

Text Generation • Updated Jan 11 • 1.76k
EleutherAI/pythia-31m-seed6

Text Generation • Updated Jan 11 • 1.84k
EleutherAI/pythia-31m-seed7

Text Generation • Updated Jan 11 • 1.73k
EleutherAI/pythia-31m-seed8

Text Generation • Updated Jan 11 • 1.85k
EleutherAI/pythia-31m-seed9

Text Generation • Updated Jan 11 • 1.9k
EleutherAI/pythia-70m

95.6M • Updated Nov 21, 2023 • 574k • 83
EleutherAI/pythia-70m-seed1

Text Generation • Updated Jan 11 • 2.34k
EleutherAI/pythia-70m-seed2

Text Generation • Updated Jan 11 • 2.23k
EleutherAI/pythia-70m-seed3

Text Generation • Updated Jan 11 • 1.94k
EleutherAI/pythia-70m-seed4

Text Generation • Updated Jan 11 • 1.8k
EleutherAI/pythia-70m-seed5

Text Generation • Updated Jan 11 • 1.57k
EleutherAI/pythia-70m-seed6

Text Generation • Updated Jan 11 • 1.46k
EleutherAI/pythia-70m-seed7

Text Generation • Updated Jan 11 • 1.38k
EleutherAI/pythia-70m-seed8

Text Generation • Updated Jan 11 • 1.61k
EleutherAI/pythia-70m-seed9

Text Generation • Updated Jan 11 • 1.37k
EleutherAI/pythia-160m

Text Generation • 0.2B • Updated Jul 9, 2023 • 3.05M • 43
EleutherAI/pythia-160m-seed1

Text Generation • 0.2B • Updated Jan 11 • 3.65k
EleutherAI/pythia-160m-seed2

Text Generation • 0.2B • Updated Jan 11 • 2.36k
EleutherAI/pythia-160m-seed3

Text Generation • 0.2B • Updated Jan 11 • 2.37k
EleutherAI/pythia-160m-seed4

Text Generation • Updated Jan 11 • 1.55k • 1
EleutherAI/pythia-160m-seed5

Text Generation • Updated Jan 11 • 1.43k
EleutherAI/pythia-160m-seed6

Text Generation • Updated Jan 11 • 1.49k
EleutherAI/pythia-160m-seed7

Text Generation • Updated Jan 11 • 1.39k
EleutherAI/pythia-160m-seed8

Text Generation • Updated Jan 11 • 1.38k
EleutherAI/pythia-160m-seed9

Text Generation • Updated Jan 11 • 1.42k
EleutherAI/pythia-410m

Text Generation • 0.5B • Updated Jul 9, 2023 • 201k • 38
EleutherAI/pythia-410m-seed1

Text Generation • Updated Jan 11 • 3.77k
EleutherAI/pythia-410m-seed2

Text Generation • Updated Jan 11 • 3.92k
EleutherAI/pythia-410m-seed3

Text Generation • Updated Jan 11 • 7.35k
EleutherAI/pythia-410m-seed4

Text Generation • Updated Jan 11 • 4.22k
EleutherAI/pythia-410m-seed5

Text Generation • Updated Jan 11 • 3.06k
EleutherAI/pythia-410m-seed6

Text Generation • Updated Jan 11 • 2.06k • 1
EleutherAI/pythia-410m-seed7

Text Generation • Updated Jan 11 • 2.42k
EleutherAI/pythia-410m-seed8

Text Generation • Updated Jan 11 • 2.21k
EleutherAI/pythia-410m-seed9

Text Generation • Updated Jan 11 • 2.15k
EleutherAI/pythia-160m-data-seed1

Text Generation • Updated Jan 11 • 713

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 • 514

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 • 516

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 • 585

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 • 522

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 • 522

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