PolyPythias - a EleutherAI Collection

EleutherAI 's Collections

Pythia Scaling Suite

Quirky Models and Datasets

Pile-T5

Quirky Math (archive)

Pile-T5 T5x Checkpoints

Sparse Autoencoders

PolyPythias

updated Apr 9

EleutherAI/polypythias-evals

Preview • Updated Sep 11, 2024 • 2.13k
EleutherAI/pile-preshuffled-seeds

Updated Feb 27 • 185 • 1

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

Text Generation • Updated Jul 26, 2023 • 234k • 23
EleutherAI/pythia-14m-seed1

Updated Dec 13, 2023 • 3.23k
EleutherAI/pythia-14m-seed2

Updated Dec 13, 2023 • 713
EleutherAI/pythia-14m-seed3

Updated Dec 18, 2023 • 407
EleutherAI/pythia-14m-seed4

Updated Dec 18, 2023 • 404
EleutherAI/pythia-14m-seed5

Updated Jan 10, 2024 • 407
EleutherAI/pythia-14m-seed6

Updated Jan 11, 2024 • 411
EleutherAI/pythia-14m-seed7

Updated Jan 26, 2024 • 401
EleutherAI/pythia-14m-seed8

Updated Jan 26, 2024 • 401
EleutherAI/pythia-14m-seed9

Updated Jan 26, 2024 • 394
EleutherAI/pythia-31m

Text Generation • Updated Jul 26, 2023 • 25.2k • 5
EleutherAI/pythia-31m-seed1

Updated Jan 13, 2024 • 1.67k
EleutherAI/pythia-31m-seed2

Updated Jan 26, 2024 • 340
EleutherAI/pythia-31m-seed3

Updated Jan 26, 2024 • 338
EleutherAI/pythia-31m-seed4

Updated Jan 26, 2024 • 340
EleutherAI/pythia-31m-seed5

Updated Jan 26, 2024 • 334
EleutherAI/pythia-31m-seed6

Updated Jan 26, 2024 • 336
EleutherAI/pythia-31m-seed7

Updated Jan 26, 2024 • 339
EleutherAI/pythia-31m-seed8

Updated Jan 26, 2024 • 338
EleutherAI/pythia-31m-seed9

Updated Jan 26, 2024 • 337
EleutherAI/pythia-70m

Updated Nov 21, 2023 • 114k • 68
EleutherAI/pythia-70m-seed1

Updated Nov 8, 2023 • 2.3k
EleutherAI/pythia-70m-seed2

Updated Nov 13, 2023 • 826
EleutherAI/pythia-70m-seed3

Updated Nov 14, 2023 • 840
EleutherAI/pythia-70m-seed4

Updated Nov 15, 2023 • 841
EleutherAI/pythia-70m-seed5

Updated Jan 13, 2024 • 648
EleutherAI/pythia-70m-seed6

Updated Jan 13, 2024 • 371
EleutherAI/pythia-70m-seed7

Updated Jan 13, 2024 • 374
EleutherAI/pythia-70m-seed8

Updated Jan 14, 2024 • 375
EleutherAI/pythia-70m-seed9

Updated Jan 14, 2024 • 375
EleutherAI/pythia-160m

Text Generation • Updated Jul 9, 2023 • 100k • 31
EleutherAI/pythia-160m-seed1

Text Generation • Updated Jan 4, 2024 • 2.64k
EleutherAI/pythia-160m-seed2

Text Generation • Updated Jan 4, 2024 • 594
EleutherAI/pythia-160m-seed3

Text Generation • Updated Jan 4, 2024 • 683
EleutherAI/pythia-160m-seed4

Updated Nov 8, 2023 • 103 • 1
EleutherAI/pythia-160m-seed5

Updated Jan 14, 2024 • 142
EleutherAI/pythia-160m-seed6

Updated Jan 14, 2024 • 50
EleutherAI/pythia-160m-seed7

Updated Jan 15, 2024 • 54
EleutherAI/pythia-160m-seed8

Updated Jan 16, 2024 • 54
EleutherAI/pythia-160m-seed9

Updated Jan 19, 2024 • 50
EleutherAI/pythia-410m

Text Generation • Updated Jul 9, 2023 • 107k • 28
EleutherAI/pythia-410m-seed1

Updated Nov 28, 2023 • 4.51k
EleutherAI/pythia-410m-seed2

Updated Nov 29, 2023 • 457
EleutherAI/pythia-410m-seed3

Updated Jan 24, 2024 • 446
EleutherAI/pythia-410m-seed4

Updated Jan 25, 2024 • 443
EleutherAI/pythia-410m-seed5

Updated Feb 4, 2024 • 433
EleutherAI/pythia-410m-seed6

Updated Jan 29, 2024 • 44
EleutherAI/pythia-410m-seed7

Updated Feb 4, 2024 • 44
EleutherAI/pythia-410m-seed8

Updated Feb 4, 2024 • 43
EleutherAI/pythia-410m-seed9

Updated Feb 4, 2024 • 51
EleutherAI/pythia-160m-data-seed1

Updated Jan 22, 2024

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

Updated Jan 22, 2024

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

Updated Jan 24, 2024

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

Updated Jan 16, 2024

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

Updated Jan 17, 2024

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

Updated Jan 17, 2024

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