I could provide some pretrained model

您好，我最近因为批量的训练一批robust model，选择你们的仓库作为训练框架，在imagenet-net训练了 convnext_small（40.78@AA), convnext_large(在训练中) , swin_large(在训练中) ,mvitv2_base(在训练中) 。但很耗时.... 所以，环保起见，我觉得可能我把它po出来让别人再利用可能更好点，如果您觉得这个合适的话，请联系我 bizhe.bai@mail.utoronto.ca

Issue #2 proposes sharing pretrained ConvNeXt, Swin, and MViTv2 models trained on ImageNet-Nets; start by clarifying whether the repository should host or document these artifacts. Done is not defined in the issue, so confirm the expected contribution and acceptance criteria before coding.

Written by the indexing model from the issue text.