PolyPythias
- Preview • Updated • 146
EleutherAI/pile-preshuffled-seeds
Updated • 689 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 11.3k • 29 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 1.75k -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 1.51k -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 1.45k -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 1.44k -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 1.62k -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 1.61k -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 1.6k -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 1.62k -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 1.62k -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 1.37k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 1.31k -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 1.32k -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 1.3k -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 1.3k -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 1.3k -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 1.32k -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 1.31k -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 1.3k -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 1.32k -
EleutherAI/pythia-70m
95.6M • Updated • 575k • 81 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 2.03k -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 2.05k -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 1.92k -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 1.94k -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 1.87k -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 1.84k -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 1.78k -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 1.76k -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 1.76k -
EleutherAI/pythia-160m
Text Generation • 0.2B • Updated • 3M • 42 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 4.12k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 2.83k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 3.38k -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 1.93k • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 1.99k -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 1.92k -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 1.93k -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 1.91k -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 1.89k -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 120k • 36 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 3.02k -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 3.27k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 4.3k -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 2.9k -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 2.69k -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 2.56k • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 2.59k -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 2.36k -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 2.44k
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 1.14kNote 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 • 1.12kNote 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 • 1.12kNote 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 • 1.14kNote 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 • 1.11kNote 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 • 1.12kNote Version where the data order and weight initialization seeds are decoupled. Here, only the weight initialization seed is different from pythia-160m ("seed 0").
-
PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs
Paper • 2503.09543 • Published