PolyPythias
- Preview • Updated • 2.67k
EleutherAI/pile-preshuffled-seeds
Updated • 851 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 14.6k • 32 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 2.5k • 1 -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 2.08k -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 1.96k -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 1.97k -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 2.09k -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 1.82k -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 1.61k -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 1.61k -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 2.12k -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 1.31k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 1.92k -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 1.9k -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 1.93k -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 1.86k -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 1.82k -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 1.4k -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 1.38k -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 1.37k -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 992 -
EleutherAI/pythia-70m
95.6M • Updated • 504k • 86 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 3.06k -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 3.32k -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 2.85k -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 2.76k -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 2.27k -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 1.81k -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 1.78k -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 1.78k -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 1.53k -
EleutherAI/pythia-160m
Text Generation • 0.2B • Updated • 3.45M • 49 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 8.34k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 7.3k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 9.47k -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 3.96k • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 3.46k -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 2.54k -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 2.52k -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 2.6k -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 1.72k -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 220k • 40 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 3.84k -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 3.39k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 3.03k -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 2.49k -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 2.18k -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 2.21k • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 2.06k -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 2.01k -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 1.42k
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 1.46kNote 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 • 1.19kNote 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 • 1.53kNote 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 • 977Note 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