PolyPythias
- Preview • Updated • 2.56k
EleutherAI/pile-preshuffled-seeds
Updated • 792 • 1Note Training data information for each seed.
-
EleutherAI/pythia-14m-deduped
Text Generation • 39.2M • Updated • 12.7k • 32 -
EleutherAI/pythia-14m-seed1
Text Generation • Updated • 1.95k • 1 -
EleutherAI/pythia-14m-seed2
Text Generation • Updated • 1.49k -
EleutherAI/pythia-14m-seed3
Text Generation • Updated • 1.46k -
EleutherAI/pythia-14m-seed4
Text Generation • Updated • 1.76k -
EleutherAI/pythia-14m-seed5
Text Generation • Updated • 1.87k -
EleutherAI/pythia-14m-seed6
Text Generation • Updated • 1.48k -
EleutherAI/pythia-14m-seed7
Text Generation • Updated • 1.39k -
EleutherAI/pythia-14m-seed8
Text Generation • Updated • 1.41k -
EleutherAI/pythia-14m-seed9
Text Generation • Updated • 2.26k -
EleutherAI/pythia-31m-deduped
Text Generation • 55.7M • Updated • 1.39k • 5 -
EleutherAI/pythia-31m-seed1
Text Generation • Updated • 1.89k -
EleutherAI/pythia-31m-seed2
Text Generation • Updated • 1.8k -
EleutherAI/pythia-31m-seed3
Text Generation • Updated • 1.89k -
EleutherAI/pythia-31m-seed4
Text Generation • Updated • 1.81k -
EleutherAI/pythia-31m-seed5
Text Generation • Updated • 1.78k -
EleutherAI/pythia-31m-seed6
Text Generation • Updated • 1.33k -
EleutherAI/pythia-31m-seed7
Text Generation • Updated • 1.24k -
EleutherAI/pythia-31m-seed8
Text Generation • Updated • 1.23k -
EleutherAI/pythia-31m-seed9
Text Generation • Updated • 1.2k -
EleutherAI/pythia-70m
95.6M • Updated • 382k • 87 -
EleutherAI/pythia-70m-seed1
Text Generation • Updated • 3.42k -
EleutherAI/pythia-70m-seed2
Text Generation • Updated • 3.4k -
EleutherAI/pythia-70m-seed3
Text Generation • Updated • 3.01k -
EleutherAI/pythia-70m-seed4
Text Generation • Updated • 2.76k -
EleutherAI/pythia-70m-seed5
Text Generation • Updated • 2.24k -
EleutherAI/pythia-70m-seed6
Text Generation • Updated • 1.85k -
EleutherAI/pythia-70m-seed7
Text Generation • Updated • 1.72k -
EleutherAI/pythia-70m-seed8
Text Generation • Updated • 1.67k -
EleutherAI/pythia-70m-seed9
Text Generation • Updated • 1.75k -
EleutherAI/pythia-160m
Text Generation • 0.2B • Updated • 3.43M • 61 -
EleutherAI/pythia-160m-seed1
Text Generation • 0.2B • Updated • 14.3k -
EleutherAI/pythia-160m-seed2
Text Generation • 0.2B • Updated • 13.8k -
EleutherAI/pythia-160m-seed3
Text Generation • 0.2B • Updated • 13.6k -
EleutherAI/pythia-160m-seed4
Text Generation • Updated • 3.22k • 1 -
EleutherAI/pythia-160m-seed5
Text Generation • Updated • 2.75k -
EleutherAI/pythia-160m-seed6
Text Generation • Updated • 2.16k -
EleutherAI/pythia-160m-seed7
Text Generation • Updated • 2.13k -
EleutherAI/pythia-160m-seed8
Text Generation • Updated • 2.21k -
EleutherAI/pythia-160m-seed9
Text Generation • Updated • 1.96k -
EleutherAI/pythia-410m
Text Generation • 0.5B • Updated • 180k • 41 -
EleutherAI/pythia-410m-seed1
Text Generation • Updated • 3.31k -
EleutherAI/pythia-410m-seed2
Text Generation • Updated • 2.92k -
EleutherAI/pythia-410m-seed3
Text Generation • Updated • 2.66k -
EleutherAI/pythia-410m-seed4
Text Generation • Updated • 2.43k -
EleutherAI/pythia-410m-seed5
Text Generation • Updated • 2.1k -
EleutherAI/pythia-410m-seed6
Text Generation • Updated • 1.88k • 1 -
EleutherAI/pythia-410m-seed7
Text Generation • Updated • 1.83k -
EleutherAI/pythia-410m-seed8
Text Generation • Updated • 1.79k -
EleutherAI/pythia-410m-seed9
Text Generation • Updated • 1.71k
EleutherAI/pythia-160m-data-seed1
Text Generation • Updated • 1.37kNote 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 • 1.14kNote 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 • 1.1kNote 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 • 1.35kNote 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 • 1.15kNote 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 • 1.03kNote 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