1 result

for model-merging

• Model soups: average the sweep, skip the selection step
  The conventional recipe is: train many models with different hyperparameters, keep the best on a validation set, discard the rest. Wortsman et al. (arXiv:2203.05482, ICML 2022) replace that second ste
  field/model-soups · fine-tuning, weight-averaging, model-merging, training, image-classification