PolyPythias
- Preview • Updated • 46
EleutherAI/pile-preshuffled-seeds
Updated • 169 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 11.4k • 29 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 1.63k -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 1.91k -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 1.84k -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 2.57k -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 2.88k -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 2.23k -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 1.5k -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 2.72k -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 1.82k -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 3.67k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 2.78k -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 2.64k -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 2.7k -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 2.7k -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 2.69k -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 2.67k -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 2.63k -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 2.57k -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 2.58k -
EleutherAI/pythia-70m
95.6M • Updated • 715k • 81 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 3.47k -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 3.32k -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 3.32k -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 3.04k -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 2.98k -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 3.2k -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 3.24k -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 3.05k -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 3.12k -
EleutherAI/pythia-160m
Text Generation • Updated • 3.15M • 41 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 5.74k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 6.08k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 5.28k -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 3.96k • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 3.94k -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 3.88k -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 3.76k -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 3.87k -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 4.38k -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 191k • 37 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 7.48k -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 4.31k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 3.8k -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 3.63k -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 4k -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 3.69k • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 3.72k -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 3.63k -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 3.9k
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 2.21kNote 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 • 2.2kNote 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 • 2.21kNote 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 • 2.2kNote 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 • 2.22kNote 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 • 2.21kNote 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