PolyPythias
-
Preview • Updated • 97
EleutherAI/pile-preshuffled-seeds
Updated • 282 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 55.9k • 28 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 122 -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 224 -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 116 -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 109 -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 147 -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 136 -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 147 -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 142 -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 138 -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 3.33k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 114 -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 115 -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 107 -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 101 -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 108 -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 113 -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 112 -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 107 -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 109 -
EleutherAI/pythia-70m
95.6M • Updated • 76.7k • 78 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 897 -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 576 -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 558 -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 525 -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 552 -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 529 -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 529 -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 529 -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 518 -
EleutherAI/pythia-160m
Text Generation • Updated • 1.14M • 38 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 963 -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 909 -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 904 -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 848 • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 609 -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 593 -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 586 -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 592 -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 578 -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 66.4k • 36 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 653 -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 1.26k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 611 -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 579 -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 532 -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 856 • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 537 -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 573 -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 716
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 141Note 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 • 145Note 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 • 148Note 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 • 245Note 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 • 212Note 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 • 202Note 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