PolyPythias
-
Preview • Updated • 1.98k
EleutherAI/pile-preshuffled-seeds
Updated • 53 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m
Text Generation • 39.2M • Updated • 37.9k • 26 -
EleutherAI/pythia-14m-seed1
Updated -
EleutherAI/pythia-14m-seed2
Updated -
EleutherAI/pythia-14m-seed3
Updated -
EleutherAI/pythia-14m-seed4
Updated -
EleutherAI/pythia-14m-seed5
Updated -
EleutherAI/pythia-14m-seed6
Updated -
EleutherAI/pythia-14m-seed7
Updated -
EleutherAI/pythia-14m-seed8
Updated -
EleutherAI/pythia-14m-seed9
Updated -
EleutherAI/pythia-31m
Text Generation • 55.7M • Updated • 5.21k • 5 -
EleutherAI/pythia-31m-seed1
Updated -
EleutherAI/pythia-31m-seed2
Updated -
EleutherAI/pythia-31m-seed3
Updated -
EleutherAI/pythia-31m-seed4
Updated -
EleutherAI/pythia-31m-seed5
Updated -
EleutherAI/pythia-31m-seed6
Updated -
EleutherAI/pythia-31m-seed7
Updated -
EleutherAI/pythia-31m-seed8
Updated -
EleutherAI/pythia-31m-seed9
Updated -
EleutherAI/pythia-70m
95.6M • Updated • 66.7k • 77 -
EleutherAI/pythia-70m-seed1
Updated • 1.2k -
EleutherAI/pythia-70m-seed2
Updated • 2.4k -
EleutherAI/pythia-70m-seed3
Updated • 2.68k -
EleutherAI/pythia-70m-seed4
Updated -
EleutherAI/pythia-70m-seed5
Updated -
EleutherAI/pythia-70m-seed6
Updated -
EleutherAI/pythia-70m-seed7
Updated -
EleutherAI/pythia-70m-seed8
Updated -
EleutherAI/pythia-70m-seed9
Updated -
EleutherAI/pythia-160m
Text Generation • 0.2B • Updated • 91.9k • 36 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 315 -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 330 -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 265 -
EleutherAI/pythia-160m-seed4
Updated • 1 -
EleutherAI/pythia-160m-seed5
Updated -
EleutherAI/pythia-160m-seed6
Updated -
EleutherAI/pythia-160m-seed7
Updated -
EleutherAI/pythia-160m-seed8
Updated -
EleutherAI/pythia-160m-seed9
Updated -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 38.9k • 36 -
EleutherAI/pythia-410m-seed1
Updated • 17 -
EleutherAI/pythia-410m-seed2
Updated • 13 -
EleutherAI/pythia-410m-seed3
Updated -
EleutherAI/pythia-410m-seed4
Updated -
EleutherAI/pythia-410m-seed5
Updated -
EleutherAI/pythia-410m-seed6
Updated -
EleutherAI/pythia-410m-seed7
Updated -
EleutherAI/pythia-410m-seed8
Updated -
EleutherAI/pythia-410m-seed9
Updated
EleutherAI/pythia-160m-data-seed1
UpdatedNote 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
UpdatedNote 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
UpdatedNote 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
UpdatedNote 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
UpdatedNote 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
UpdatedNote 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