PolyPythias
- Preview • Updated • 47
EleutherAI/pile-preshuffled-seeds
Updated • 182 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 8.77k • 29 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 1.28k -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 1.63k -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 1.68k -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 2.45k -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 2.7k -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 2.13k -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 1.45k -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 2.46k -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 1.68k -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 3.82k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 2.7k -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 2.52k -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 2.69k -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 2.44k -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 2.63k -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 2.49k -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 2.64k -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 2.4k -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 2.59k -
EleutherAI/pythia-70m
95.6M • Updated • 504k • 80 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 3.35k -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 3.05k -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 3.1k -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 2.85k -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 2.87k -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 2.86k -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 2.99k -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 2.92k -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 2.91k -
EleutherAI/pythia-160m
Text Generation • Updated • 3.05M • 39 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 6.12k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 5.84k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 5.49k -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 3.67k • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 3.53k -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 3.58k -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 3.45k -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 3.57k -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 3.97k -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 177k • 36 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 7.05k -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 3.55k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 3.65k -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 3.24k -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 3.31k -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 3.21k • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 3.21k -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 3.17k -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 3.15k
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 2.72kNote 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 • 2.42kNote 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 • 2.77kNote 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-weight-seed1
Text Generation • Updated • 2.69kNote 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 • 2.72kNote 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