PolyPythias
- Preview • Updated • 51
EleutherAI/pile-preshuffled-seeds
Updated • 225 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 21k • 29 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 5.27k -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 5.22k -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 5.11k -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 4.63k -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 5.01k -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 5.17k -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 5.26k -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 4.63k -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 5.45k -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 3.51k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 4.62k -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 4.42k -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 4.86k -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 3.25k -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 4.26k -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 4.06k -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 4.46k -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 3.22k -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 4.76k -
EleutherAI/pythia-70m
95.6M • Updated • 323k • 79 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 4.47k -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 3.72k -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 3.77k -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 3.35k -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 3.63k -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 3.33k -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 4.5k -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 4.42k -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 3.37k -
EleutherAI/pythia-160m
Text Generation • Updated • 2.53M • 39 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 5.3k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 5.36k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 5.2k -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 4.25k • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 4.7k -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 3.31k -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 4.51k -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 3.28k -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 3.48k -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 196k • 36 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 4.35k -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 4.06k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 4.2k -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 3.47k -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 3.55k -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 3.4k • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 3.46k -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 3.4k -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 3.44k
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 3.85kNote 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 • 3.77kNote 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 • 3.94kNote 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 • 2.49kNote 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 • 2.48kNote 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 • 2.51kNote 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