simarora/gdn-paper-120m-hdim1024-lr_0.0005-layers_12-dmodel_768-n_2048-head_12-numQK_1-sim Updated May 21
simarora/gdn-paper-120m-hdim1024-lr_0.0005-layers_12-dmodel_768-n_2048-head_12-numQK_1-sim Updated May 21