PolyPythias
- Preview • Updated • 54
EleutherAI/pile-preshuffled-seeds
Updated • 219 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 22k • 29 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 5.12k -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 5.22k -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 5.17k -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 4.61k -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 4.9k -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 5.16k -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 5.15k -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 4.61k -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 5.34k -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 3.49k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 4.54k -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 4.41k -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 4.78k -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 3.22k -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 4.18k -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 4.03k -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 4.38k -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 3.2k -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 4.68k -
EleutherAI/pythia-70m
95.6M • Updated • 332k • 79 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 4.42k -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 3.71k -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 3.85k -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 3.33k -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 3.58k -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 3.32k -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 4.44k -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 4.4k -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 3.32k -
EleutherAI/pythia-160m
Text Generation • Updated • 2.52M • 39 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 5.13k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 5.36k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 5.28k -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 4.24k • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 4.65k -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 3.29k -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 4.45k -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 3.27k -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 3.43k -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 194k • 36 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 4.27k -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 4.02k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 4.13k -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 3.41k -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 3.48k -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 3.35k • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 3.38k -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 3.35k -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 3.36k
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 3.82kNote 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 • 3.75kNote 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 • 3.91kNote 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 • 2.48kNote 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 • 2.47kNote 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 • 2.48kNote 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