PolyPythias
- Preview • Updated • 142
EleutherAI/pile-preshuffled-seeds
Updated • 625 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 9.95k • 29 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 2.18k -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 1.78k -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 1.67k -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 1.58k -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 1.92k -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 1.82k -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 1.62k -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 1.64k -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 1.55k -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 1.28k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 1.22k -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 1.27k -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 1.24k -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 1.36k -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 1.2k -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 1.3k -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 1.19k -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 1.2k -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 1.26k -
EleutherAI/pythia-70m
95.6M • Updated • 516k • 81 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 1.28k -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 1.21k -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 1.2k -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 1.14k -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 1.11k -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 1.13k -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 1.1k -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 1.2k -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 1.11k -
EleutherAI/pythia-160m
Text Generation • 0.2B • Updated • 2.76M • 42 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 3.17k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 1.82k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 1.93k -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 1.41k • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 1.42k -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 1.37k -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 1.34k -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 1.34k -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 1.33k -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 105k • 37 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 3.17k -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 3.2k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 7.33k -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 3.78k -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 2.77k -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 1.7k • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 2k -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 1.83k -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 1.79k
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 1.03kNote 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 • 998Note 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 • 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-weight-seed1
Text Generation • Updated • 1.02kNote 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 • 999Note 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 • 1.01kNote 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