PolyPythias
- Preview • Updated • 958
EleutherAI/pile-preshuffled-seeds
Updated • 310 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 34.2k • 30 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 1.51k -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 1.3k -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 1.15k -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 1.04k -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 1.22k -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 2.37k -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 1.11k -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 1.07k -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 1.05k -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 2.44k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 782 -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 828 -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 687 -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 665 -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 664 -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 1.25k -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 617 -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 592 -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 629 -
EleutherAI/pythia-70m
95.6M • Updated • 493k • 85 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 4.46k -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 2.82k -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 2.16k -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 1.56k -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 1.49k -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 1.75k -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 1.4k -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 1.44k -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 1.43k -
EleutherAI/pythia-160m
Text Generation • 0.2B • Updated • 3.4M • 45 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 34.9k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 31.3k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 28.3k -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 13.8k • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 13.8k -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 14.2k -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 2.57k -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 2.46k -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 2.85k -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 210k • 40 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 17.6k -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 5.28k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 3.83k -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 2.46k -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 2.11k -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 1.59k • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 1.74k -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 1.55k -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 1.55k
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 11.4kNote 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 • 4.08kNote 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 • 4.03kNote 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 • 5.31kNote 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 • 4.12kNote 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 • 3.97kNote 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