dataset
active
dataset:apertus-8b-pretraining-checkpointsApertus-8B Pretraining Checkpoints
15 pretraining checkpoints sampled from Apertus-8B ranging from 210B to 15T tokens
Neighborhood — ranked by edge-count
Papers (1)
paper
dataset:apertus-8b-pretraining-checkpoints15 pretraining checkpoints sampled from Apertus-8B ranging from 210B to 15T tokens