PolyPythias
-
Preview • Updated • 193
EleutherAI/pile-preshuffled-seeds
Updated • 214 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m
Text Generation • 39.2M • Updated • 79.6k • 25 -
EleutherAI/pythia-14m-seed1
Updated • 247 -
EleutherAI/pythia-14m-seed2
Updated • 218 -
EleutherAI/pythia-14m-seed3
Updated • 8 -
EleutherAI/pythia-14m-seed4
Updated • 5 -
EleutherAI/pythia-14m-seed5
Updated • 6 -
EleutherAI/pythia-14m-seed6
Updated • 6 -
EleutherAI/pythia-14m-seed7
Updated • 6 -
EleutherAI/pythia-14m-seed8
Updated • 6 -
EleutherAI/pythia-14m-seed9
Updated • 4 -
EleutherAI/pythia-31m
Text Generation • 55.7M • Updated • 7.3k • 5 -
EleutherAI/pythia-31m-seed1
Updated -
EleutherAI/pythia-31m-seed2
Updated -
EleutherAI/pythia-31m-seed3
Updated -
EleutherAI/pythia-31m-seed4
Updated -
EleutherAI/pythia-31m-seed5
Updated -
EleutherAI/pythia-31m-seed6
Updated -
EleutherAI/pythia-31m-seed7
Updated -
EleutherAI/pythia-31m-seed8
Updated -
EleutherAI/pythia-31m-seed9
Updated -
EleutherAI/pythia-70m
95.6M • Updated • 90.6k • 74 -
EleutherAI/pythia-70m-seed1
Updated • 5 -
EleutherAI/pythia-70m-seed2
Updated • 6 -
EleutherAI/pythia-70m-seed3
Updated • 5 -
EleutherAI/pythia-70m-seed4
Updated • 1 -
EleutherAI/pythia-70m-seed5
Updated • 2 -
EleutherAI/pythia-70m-seed6
Updated • 2 -
EleutherAI/pythia-70m-seed7
Updated • 2 -
EleutherAI/pythia-70m-seed8
Updated • 1 -
EleutherAI/pythia-70m-seed9
Updated • 4 -
EleutherAI/pythia-160m
Text Generation • 0.2B • Updated • 79.4k • 35 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 4.79k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 3.2k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 1.22k -
EleutherAI/pythia-160m-seed4
Updated • 321 • 1 -
EleutherAI/pythia-160m-seed5
Updated • 323 -
EleutherAI/pythia-160m-seed6
Updated • 323 -
EleutherAI/pythia-160m-seed7
Updated • 314 -
EleutherAI/pythia-160m-seed8
Updated • 318 -
EleutherAI/pythia-160m-seed9
Updated • 328 -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 40.6k • 35 -
EleutherAI/pythia-410m-seed1
Updated • 1.19k -
EleutherAI/pythia-410m-seed2
Updated • 318 -
EleutherAI/pythia-410m-seed3
Updated • 319 -
EleutherAI/pythia-410m-seed4
Updated • 311 -
EleutherAI/pythia-410m-seed5
Updated • 322 -
EleutherAI/pythia-410m-seed6
Updated • 312 -
EleutherAI/pythia-410m-seed7
Updated • 312 -
EleutherAI/pythia-410m-seed8
Updated • 321 -
EleutherAI/pythia-410m-seed9
Updated • 320
EleutherAI/pythia-160m-data-seed1
UpdatedNote 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
UpdatedNote 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
UpdatedNote 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
Updated • 284Note 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
UpdatedNote 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
UpdatedNote 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