PolyPythias
- Preview • Updated • 746
EleutherAI/pile-preshuffled-seeds
Updated • 645 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 33.2k • 31 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 1.96k -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 1.74k -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 1.49k -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 1.43k -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 1.43k -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 2.35k -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 1.08k -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 1.05k -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 656 -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 2.28k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 1.47k -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 1.54k -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 1.32k -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 1.31k -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 1.34k -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 1.59k -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 965 -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 932 -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 671 -
EleutherAI/pythia-70m
95.6M • Updated • 552k • 86 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 4.18k -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 3.11k -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 2.44k -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 1.79k -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 1.67k -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 1.96k -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 1.64k -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 1.68k -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 1.38k -
EleutherAI/pythia-160m
Text Generation • 0.2B • Updated • 3.44M • 45 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 11.2k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 8.44k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 22.1k -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 2.98k • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 2.74k -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 2.7k -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 2.08k -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 2.08k -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 1.46k -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 239k • 40 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 16.4k -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 5.99k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 4.41k -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 2.64k -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 2.26k -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 1.91k • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 1.94k -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 1.73k -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 1.24k
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 3.4kNote 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 • 3.06kNote 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 • 3.02kNote 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 • 2.9kNote 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 • 2.73kNote 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 • 2.74kNote 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