PolyPythias
-
Preview • Updated • 94
EleutherAI/pile-preshuffled-seeds
Updated • 308 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 61.1k • 28 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 171 -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 241 -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 111 -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 107 -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 143 -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 128 -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 140 -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 135 -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 132 -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 3.1k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 205 -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 204 -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 99 -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 94 -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 101 -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 105 -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 102 -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 99 -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 102 -
EleutherAI/pythia-70m
95.6M • Updated • 82.8k • 78 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 969 -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 652 -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 578 -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 543 -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 557 -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 528 -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 559 -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 540 -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 524 -
EleutherAI/pythia-160m
Text Generation • Updated • 1.49M • 38 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 1.12k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 1.06k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 964 -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 861 • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 617 -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 601 -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 604 -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 604 -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 588 -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 71.2k • 36 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 679 -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 1.31k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 613 -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 572 -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 542 -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 849 • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 577 -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 573 -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 726
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 134Note 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 • 136Note 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 • 139Note 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 • 249Note 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 • 218Note 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 • 210Note 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