load model error

[sxpro]

when loading "ava.ckpt.pth", i meet :

*** RuntimeError: Error(s) in loading state_dict for Swin:
Missing key(s) in state_dict: "vit.layers.3.downsample.reduction.weight", "vit.layers.3.downsample.norm.weight", "vit.layers.3.downsample.norm.bias", "vit.head.fc.weight", "vit.head.fc.bias".
Unexpected key(s) in state_dict: "vit.layers.0.downsample.reduction.weight", "vit.layers.0.downsample.norm.weight", "vit.layers.0.downsample.norm.bias", "vit.layers.0.blocks.1.attn_mask", "vit.layers.1.blocks.1.attn_mask", "vit.layers.2.blocks.1.attn_mask", "vit.layers.2.blocks.3.attn_mask", "vit.layers.2.blocks.5.attn_mask", "vit.layers.2.blocks.7.attn_mask", "vit.layers.2.blocks.9.attn_mask", "vit.layers.2.blocks.11.attn_mask", "vit.layers.2.blocks.13.attn_mask", "vit.layers.2.blocks.15.attn_mask", "vit.layers.2.blocks.17.attn_mask", "vit.head.weight", "vit.head.bias".
size mismatch for vit.layers.1.downsample.reduction.weight: copying a param with shape torch.Size([512, 1024]) from checkpoint, the shape in current model is torch.Size([256, 512]).
size mismatch for vit.layers.1.downsample.norm.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for vit.layers.1.downsample.norm.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for vit.layers.2.downsample.reduction.weight: copying a param with shape torch.Size([1024, 2048]) from checkpoint, the shape in current model is torch.Size([512, 1024]).
size mismatch for vit.layers.2.downsample.norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for vit.layers.2.downsample.norm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([512]).

Could u help me to solve this?