PolyPythias
- Preview • Updated • 58
EleutherAI/pile-preshuffled-seeds
Updated • 223 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 15.1k • 29 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 2.11k -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 1.78k -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 1.72k -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 1.59k -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 1.94k -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 1.5k -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 1.59k -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 1.8k -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 1.7k -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 2.18k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 1.83k -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 1.65k -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 1.71k -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 1.74k -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 1.76k -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 1.7k -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 1.7k -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 1.6k -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 1.65k -
EleutherAI/pythia-70m
95.6M • Updated • 678k • 81 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 4.78k -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 4.85k -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 4.82k -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 4.6k -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 4.34k -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 4.54k -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 4.38k -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 4.2k -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 4.29k -
EleutherAI/pythia-160m
Text Generation • Updated • 3.1M • 42 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 8.36k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 7.4k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 7.36k -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 4.59k • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 4.26k -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 4.16k -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 4.04k -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 4.18k -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 4.66k -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 158k • 36 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 7.39k -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 4.49k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 3.87k -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 3.51k -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 3.74k -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 3.42k • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 3.53k -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 3.38k -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 3.75k
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 1.16kNote 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 • 1.16kNote 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 • 1.16kNote 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 • 1.16kNote 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 • 1.18kNote 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 • 1.17kNote 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