UniFormer-S† head_dim=64, ImageNet-1K pretrained (224x224)

[atonyo11]

I tried load and using UniFormer-S† head_dim=64 pretrained model but I got this error:

model.load_state_dict(torch.load("uniformer_small_plus_dim64_in1k.pth"):
RuntimeError: Error(s) in loading state_dict for UniFormer: Missing key(s) in state_dict: "patch_embed1.proj.0.weight", "patch_embed1.proj.0.bias", "patch_embed1.proj.1.weight", "patch_embed1.proj.1.bias", "patch_embed1.proj.1.running_mean", "patch_embed1.proj.1.running_var", "patch_embed1.proj.3.weight", "patch_embed1.proj.3.bias", "patch_embed1.proj.4.weight", "patch_embed1.proj.4.bias", "patch_embed1.proj.4.running_mean", "patch_embed1.proj.4.running_var", "patch_embed2.proj.0.weight", "patch_embed2.proj.0.bias", "patch_embed2.proj.1.weight", "patch_embed2.proj.1.bias", "patch_embed2.proj.1.running_mean", "patch_embed2.proj.1.running_var", "patch_embed3.proj.0.weight", "patch_embed3.proj.0.bias", "patch_embed3.proj.1.weight", "patch_embed3.proj.1.bias", "patch_embed3.proj.1.running_mean", "patch_embed3.proj.1.running_var", "patch_embed4.proj.0.weight", "patch_embed4.proj.0.bias", "patch_embed4.proj.1.weight", "patch_embed4.proj.1.bias", "patch_embed4.proj.1.running_mean", "patch_embed4.proj.1.running_var", "blocks1.0.pos_embed.weight", "blocks1.0.pos_embed.bias", "blocks1.0.norm1.weight", "blocks1.0.norm1.bias", "blocks1.0.norm1.running_mean", "blocks1.0.norm1.running_var", "blocks1.0.conv1.weight", "blocks1.0.conv1.bias", "blocks1.0.conv2.weight", "blocks1.0.conv2.bias", "blocks1.0.attn.weight", "blocks1.0.attn.bias", "blocks1.0.norm2.weight", "blocks1.0.norm2.bias", "blocks1.0.norm2.running_mean", "blocks1.0.norm2.running_var", "blocks1.0.mlp.fc1.weight", "blocks1.0.mlp.fc1.bias", "blocks1.0.mlp.fc2.weight", "blocks1.0.mlp.fc... Unexpected key(s) in state_dict: "model".

With model.load_state_dict(torch.load("uniformer_small_plus_in1k.pth"), The model loaded well. Could you prove correct pretrained model for UniFormer-S† head_dim=64? Thank you in advance.