PolyPythias
- Preview • Updated • 3.1k
EleutherAI/pile-preshuffled-seeds
Updated • 358 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 15.3k • 30 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 2.92k -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 1.94k -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 1.94k -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 1.42k -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 1.9k -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 1.76k -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 1.75k -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 1.46k -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 1.74k -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 1.14k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 1.27k -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 1.13k -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 1.09k -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 1.02k -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 947 -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 1.02k -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 947 -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 966 -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 1.14k -
EleutherAI/pythia-70m
95.6M • Updated • 505k • 85 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 8.47k -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 8.28k -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 1.68k -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 1.33k -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 1.35k -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 1.62k -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 1.44k -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 1.46k -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 1.32k -
EleutherAI/pythia-160m
Text Generation • 0.2B • Updated • 3.51M • 45 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 58.8k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 56k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 33.6k -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 17.2k • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 17.4k -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 17.7k -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 7.2k -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 7.12k -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 6.29k -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 213k • 39 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 21.5k -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 19.3k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 5.92k -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 5.25k -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 5.2k -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 5k • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 5.07k -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 5.84k -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 6.42k
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 99.1kNote 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 • 14.3kNote 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 • 9.72kNote 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 • 33.6kNote 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 • 14.9kNote 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 • 7.45kNote 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