PolyPythias
- Preview • Updated • 51
EleutherAI/pile-preshuffled-seeds
Updated • 232 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 21.7k • 29 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 5.06k -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 5.19k -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 5.14k -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 4.28k -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 4.56k -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 5.08k -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 5.12k -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 4.29k -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 5.3k -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 3.1k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 4.25k -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 4.12k -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 4.46k -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 2.93k -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 3.86k -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 3.75k -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 4.06k -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 2.92k -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 4.35k -
EleutherAI/pythia-70m
95.6M • Updated • 323k • 79 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 4.06k -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 3.46k -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 3.61k -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 3.09k -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 3.35k -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 3.07k -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 4.18k -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 4.13k -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 3.07k -
EleutherAI/pythia-160m
Text Generation • Updated • 2.55M • 39 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 5.08k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 5.36k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 5.29k -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 3.96k • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 4.37k -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 3.05k -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 4.18k -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 3.03k -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 3.18k -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 176k • 36 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 3.83k -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 3.71k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 3.8k -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 3.07k -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 3.14k -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 3.01k • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 3.04k -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 3.01k -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 3.01k
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 3.52kNote 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 • 3.45kNote 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-seed3
Text Generation • Updated • 3.6kNote 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 • 2.18kNote 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 • 2.18kNote 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