PolyPythias
- Preview • Updated • 2.72k
EleutherAI/pile-preshuffled-seeds
Updated • 829 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 15k • 32 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 2.42k • 1 -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 2k -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 1.93k -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 1.93k -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 2.02k -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 1.77k -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 1.54k -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 1.56k -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 2.07k -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 1.13k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 1.85k -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 1.84k -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 1.89k -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 1.82k -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 1.76k -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 1.35k -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 1.32k -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 1.32k -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 941 -
EleutherAI/pythia-70m
95.6M • Updated • 515k • 86 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 2.96k -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 3.22k -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 2.77k -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 2.69k -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 2.17k -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 1.73k -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 1.7k -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 1.7k -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 1.45k -
EleutherAI/pythia-160m
Text Generation • 0.2B • Updated • 3.46M • 47 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 7.83k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 7.06k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 22.6k -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 3.87k • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 3.35k -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 2.45k -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 2.4k -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 2.49k -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 1.63k -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 223k • 40 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 3.8k -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 3.35k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 3.01k -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 2.47k -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 2.09k -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 2.12k • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 1.98k -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 1.92k -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 1.35k
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 1.45kNote 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 • 1.28kNote 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 • 1.16kNote 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 • 1.51kNote 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 • 1.08kNote 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 • 969Note 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