PolyPythias
- Preview • Updated • 50
EleutherAI/pile-preshuffled-seeds
Updated • 186 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 12k • 29 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 1.86k -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 1.59k -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 1.56k -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 2.27k -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 2.66k -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 1.98k -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 1.4k -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 2.47k -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 1.56k -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 2.97k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 2.53k -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 2.34k -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 2.42k -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 2.42k -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 2.44k -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 2.38k -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 2.38k -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 2.27k -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 2.33k -
EleutherAI/pythia-70m
95.6M • Updated • 671k • 81 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 4.31k -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 4.19k -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 4.19k -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 3.89k -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 3.66k -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 3.89k -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 3.75k -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 3.59k -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 3.62k -
EleutherAI/pythia-160m
Text Generation • Updated • 3.17M • 41 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 5.92k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 6.22k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 5.4k -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 4.1k • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 3.96k -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 3.83k -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 3.74k -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 3.86k -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 4.38k -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 172k • 37 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 7.46k -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 4.31k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 3.73k -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 3.54k -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 3.76k -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 3.44k • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 3.51k -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 3.39k -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 3.7k
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 1.84kNote 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 • 1.82kNote 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 • 1.84kNote 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 • 1.83kNote 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 • 1.84kNote 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 • 1.83kNote 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