PolyPythias
- Preview • Updated • 54
EleutherAI/pile-preshuffled-seeds
Updated • 218 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 21.2k • 29 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 5.04k -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 5.14k -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 5.06k -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 3.66k -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 3.94k -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 4.5k -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 5.14k -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 3.72k -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 5.22k -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 2.47k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 3.64k -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 3.53k -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 3.86k -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 2.33k -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 3.26k -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 3.16k -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 3.47k -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 2.33k -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 3.75k -
EleutherAI/pythia-70m
95.6M • Updated • 288k • 79 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 3.45k -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 2.83k -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 2.98k -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 2.47k -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 2.72k -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 2.44k -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 3.54k -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 3.5k -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 2.46k -
EleutherAI/pythia-160m
Text Generation • Updated • 2.53M • 39 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 5.05k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 4.56k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 4.86k -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 3.34k • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 3.74k -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 2.42k -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 3.56k -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 2.4k -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 2.54k -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 157k • 36 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 3.2k -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 3.08k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 3.17k -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 2.44k -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 2.49k -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 2.38k • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 2.41k -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 2.37k -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 2.39k
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 2.88kNote 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 • 2.82kNote 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 • 2.97kNote 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 • 1.57kNote 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 • 1.56kNote 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 • 1.54kNote 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