PolyPythias
- Preview • Updated • 1.78k
EleutherAI/pile-preshuffled-seeds
Updated • 95 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 11.1k • 29 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 1.65k -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 1.49k -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 1.38k -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 1.32k -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 1.75k -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 2.37k -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 1.95k -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 2.01k -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 1.86k -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 2.22k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 1.78k -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 1.93k -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 1.75k -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 1.91k -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 1.69k -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 1.76k -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 1.65k -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 1.77k -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 1.82k -
EleutherAI/pythia-70m
95.6M • Updated • 580k • 83 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 2.26k -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 2.12k -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 1.83k -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 1.71k -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 1.48k -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 1.38k -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 1.3k -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 1.52k -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 1.29k -
EleutherAI/pythia-160m
Text Generation • 0.2B • Updated • 2.99M • 43 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 3.34k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 2.29k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 2.33k -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 1.45k • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 1.33k -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 1.39k -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 1.31k -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 1.31k -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 1.35k -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 260k • 38 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 2.68k -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 2.81k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 2.81k -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 2.78k -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 2.25k -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 1.95k • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 2.24k -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 2.1k -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 2.04k
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 634Note 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 • 442Note 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 • 443Note 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 • 510Note 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 • 450Note 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 • 447Note 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