Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

RuntimeError: Error(s) in loading state_dict for DehazeFormer: #34

Open
zhengchaobing opened this issue Oct 5, 2024 · 0 comments
Open

Comments

@zhengchaobing
Copy link

Missing key(s) in state_dict: "layer1.blocks.6.norm1.weight", "layer1.blocks.6.norm1.bias", "layer1.blocks.6.norm1.meta1.weight", "layer1.blocks.6.norm1.meta1.bias", "layer1.blocks.6.norm1.meta2.weight", "layer1.blocks.6.norm1.meta2.bias", "layer1.blocks.6.attn.QK.weight", "layer1.blocks.6.attn.QK.bias", "layer1.blocks.6.attn.attn.relative_positions", "layer1.blocks.6.attn.attn.meta.0.weight", "layer1.blocks.6.attn.attn.meta.0.bias", "layer1.blocks.6.attn.attn.meta.2.weight", "layer1.blocks.6.attn.attn.meta.2.bias", "layer1.blocks.7.norm1.weight", "layer1.blocks.7.norm1.bias", "layer1.blocks.7.norm1.meta1.weight", "layer1.blocks.7.norm1.meta1.bias", "layer1.blocks.7.norm1.meta2.weight", "layer1.blocks.7.norm1.meta2.bias", "layer1.blocks.7.attn.QK.weight", "layer1.blocks.7.attn.QK.bias", "layer1.blocks.7.attn.attn.relative_positions", "layer1.blocks.7.attn.attn.meta.0.weight", "layer1.blocks.7.attn.attn.meta.0.bias", "layer1.blocks.7.attn.attn.meta.2.weight", "layer1.blocks.7.attn.attn.meta.2.bias", "layer2.blocks.4.norm1.weight", "layer2.blocks.4.norm1.bias", "layer2.blocks.4.norm1.meta1.weight", "layer2.blocks.4.norm1.meta1.bias", "layer2.blocks.4.norm1.meta2.weight", "layer2.blocks.4.norm1.meta2.bias", "layer2.blocks.4.attn.QK.weight", "layer2.blocks.4.attn.QK.bias", "layer2.blocks.4.attn.attn.relative_positions", "layer2.blocks.4.attn.attn.meta.0.weight", "layer2.blocks.4.attn.attn.meta.0.bias", "layer2.blocks.4.attn.attn.meta.2.weight", "layer2.blocks.4.attn.attn.meta.2.bias", "layer2.blocks.5.norm1.weight", "layer2.blocks.5.norm1.bias", "layer2.blocks.5.norm1.meta1.weight", "layer2.blocks.5.norm1.meta1.bias", "layer2.blocks.5.norm1.meta2.weight", "layer2.blocks.5.norm1.meta2.bias", "layer2.blocks.5.attn.QK.weight", "layer2.blocks.5.attn.QK.bias", "layer2.blocks.5.attn.attn.relative_positions", "layer2.blocks.5.attn.attn.meta.0.weight", "layer2.blocks.5.attn.attn.meta.0.bias", "layer2.blocks.5.attn.attn.meta.2.weight", "layer2.blocks.5.attn.attn.meta.2.bias", "layer2.blocks.6.norm1.weight", "layer2.blocks.6.norm1.bias", "layer2.blocks.6.norm1.meta1.weight", "layer2.blocks.6.norm1.meta1.bias", "layer2.blocks.6.norm1.meta2.weight", "layer2.blocks.6.norm1.meta2.bias", "layer2.blocks.6.attn.QK.weight", "layer2.blocks.6.attn.QK.bias", "layer2.blocks.6.attn.attn.relative_positions", "layer2.blocks.6.attn.attn.meta.0.weight", "layer2.blocks.6.attn.attn.meta.0.bias", "layer2.blocks.6.attn.attn.meta.2.weight", "layer2.blocks.6.attn.attn.meta.2.bias", "layer2.blocks.7.norm1.weight", "layer2.blocks.7.norm1.bias", "layer2.blocks.7.norm1.meta1.weight", "layer2.blocks.7.norm1.meta1.bias", "layer2.blocks.7.norm1.meta2.weight", "layer2.blocks.7.norm1.meta2.bias", "layer2.blocks.7.attn.QK.weight", "layer2.blocks.7.attn.QK.bias", "layer2.blocks.7.attn.attn.relative_positions", "layer2.blocks.7.attn.attn.meta.0.weight", "layer2.blocks.7.attn.attn.meta.0.bias", "layer2.blocks.7.attn.attn.meta.2.weight", "layer2.blocks.7.attn.attn.meta.2.bias", "layer3.blocks.2.norm1.weight", "layer3.blocks.2.norm1.bias", "layer3.blocks.2.norm1.meta1.weight", "layer3.blocks.2.norm1.meta1.bias", "layer3.blocks.2.norm1.meta2.weight", "layer3.blocks.2.norm1.meta2.bias", "layer3.blocks.2.attn.QK.weight", "layer3.blocks.2.attn.QK.bias", "layer3.blocks.2.attn.attn.relative_positions", "layer3.blocks.2.attn.attn.meta.0.weight", "layer3.blocks.2.attn.attn.meta.0.bias", "layer3.blocks.2.attn.attn.meta.2.weight", "layer3.blocks.2.attn.attn.meta.2.bias", "layer3.blocks.3.norm1.weight", "layer3.blocks.3.norm1.bias", "layer3.blocks.3.norm1.meta1.weight", "layer3.blocks.3.norm1.meta1.bias", "layer3.blocks.3.norm1.meta2.weight", "layer3.blocks.3.norm1.meta2.bias", "layer3.blocks.3.attn.QK.weight", "layer3.blocks.3.attn.QK.bias", "layer3.blocks.3.attn.attn.relative_positions", "layer3.blocks.3.attn.attn.meta.0.weight", "layer3.blocks.3.attn.attn.meta.0.bias", "layer3.blocks.3.attn.attn.meta.2.weight", "layer3.blocks.3.attn.attn.meta.2.bias".
Unexpected key(s) in state_dict: "layer1.blocks.8.attn.conv.weight", "layer1.blocks.8.attn.conv.bias", "layer1.blocks.8.attn.V.weight", "layer1.blocks.8.attn.V.bias", "layer1.blocks.8.attn.proj.weight", "layer1.blocks.8.attn.proj.bias", "layer1.blocks.8.mlp.mlp.0.weight", "layer1.blocks.8.mlp.mlp.0.bias", "layer1.blocks.8.mlp.mlp.2.weight", "layer1.blocks.8.mlp.mlp.2.bias", "layer1.blocks.9.attn.conv.weight", "layer1.blocks.9.attn.conv.bias", "layer1.blocks.9.attn.V.weight", "layer1.blocks.9.attn.V.bias", "layer1.blocks.9.attn.proj.weight", "layer1.blocks.9.attn.proj.bias", "layer1.blocks.9.mlp.mlp.0.weight", "layer1.blocks.9.mlp.mlp.0.bias", "layer1.blocks.9.mlp.mlp.2.weight", "layer1.blocks.9.mlp.mlp.2.bias", "layer1.blocks.10.attn.conv.weight", "layer1.blocks.10.attn.conv.bias", "layer1.blocks.10.attn.V.weight", "layer1.blocks.10.attn.V.bias", "layer1.blocks.10.attn.proj.weight", "layer1.blocks.10.attn.proj.bias", "layer1.blocks.10.mlp.mlp.0.weight", "layer1.blocks.10.mlp.mlp.0.bias", "layer1.blocks.10.mlp.mlp.2.weight", "layer1.blocks.10.mlp.mlp.2.bias", "layer1.blocks.11.attn.conv.weight", "layer1.blocks.11.attn.conv.bias", "layer1.blocks.11.attn.V.weight", "layer1.blocks.11.attn.V.bias", "layer1.blocks.11.attn.proj.weight", "layer1.blocks.11.attn.proj.bias", "layer1.blocks.11.mlp.mlp.0.weight", "layer1.blocks.11.mlp.mlp.0.bias", "layer1.blocks.11.mlp.mlp.2.weight", "layer1.blocks.11.mlp.mlp.2.bias", "layer1.blocks.12.norm1.weight", "layer1.blocks.12.norm1.bias", "layer1.blocks.12.norm1.meta1.weight", "layer1.blocks.12.norm1.meta1.bias", "layer1.blocks.12.norm1.meta2.weight", "layer1.blocks.12.norm1.meta2.bias", "layer1.blocks.12.attn.conv.weight", "layer1.blocks.12.attn.conv.bias", "layer1.blocks.12.attn.V.weight", "layer1.blocks.12.attn.V.bias", "layer1.blocks.12.attn.proj.weight", "layer1.blocks.12.attn.proj.bias", "layer1.blocks.12.attn.QK.weight", "layer1.blocks.12.attn.QK.bias", "layer1.blocks.12.attn.attn.relative_positions", "layer1.blocks.12.attn.attn.meta.0.weight", "layer1.blocks.12.attn.attn.meta.0.bias", "layer1.blocks.12.attn.attn.meta.2.weight", "layer1.blocks.12.attn.attn.meta.2.bias", "layer1.blocks.12.mlp.mlp.0.weight", "layer1.blocks.12.mlp.mlp.0.bias", "layer1.blocks.12.mlp.mlp.2.weight", "layer1.blocks.12.mlp.mlp.2.bias", "layer1.blocks.13.norm1.weight", "layer1.blocks.13.norm1.bias", "layer1.blocks.13.norm1.meta1.weight", "layer1.blocks.13.norm1.meta1.bias", "layer1.blocks.13.norm1.meta2.weight", "layer1.blocks.13.norm1.meta2.bias", "layer1.blocks.13.attn.conv.weight", "layer1.blocks.13.attn.conv.bias", "layer1.blocks.13.attn.V.weight", "layer1.blocks.13.attn.V.bias", "layer1.blocks.13.attn.proj.weight", "layer1.blocks.13.attn.proj.bias", "layer1.blocks.13.attn.QK.weight", "layer1.blocks.13.attn.QK.bias", "layer1.blocks.13.attn.attn.relative_positions", "layer1.blocks.13.attn.attn.meta.0.weight", "layer1.blocks.13.attn.attn.meta.0.bias", "layer1.blocks.13.attn.attn.meta.2.weight", "layer1.blocks.13.attn.attn.meta.2.bias", "layer1.blocks.13.mlp.mlp.0.weight", "layer1.blocks.13.mlp.mlp.0.bias", "layer1.blocks.13.mlp.mlp.2.weight", "layer1.blocks.13.mlp.mlp.2.bias", "layer1.blocks.14.norm1.weight", "layer1.blocks.14.norm1.bias", "layer1.blocks.14.norm1.meta1.weight", "layer1.blocks.14.norm1.meta1.bias", "layer1.blocks.14.norm1.meta2.weight", "layer1.blocks.14.norm1.meta2.bias", "layer1.blocks.14.attn.conv.weight", "layer1.blocks.14.attn.conv.bias", "layer1.blocks.14.attn.V.weight", "layer1.blocks.14.attn.V.bias", "layer1.blocks.14.attn.proj.weight", "layer1.blocks.14.attn.proj.bias", "layer1.blocks.14.attn.QK.weight", "layer1.blocks.14.attn.QK.bias", "layer1.blocks.14.attn.attn.relative_positions", "layer1.blocks.14.attn.attn.meta.0.weight", "layer1.blocks.14.attn.attn.meta.0.bias", "layer1.blocks.14.attn.attn.meta.2.weight", "layer1.blocks.14.attn.attn.meta.2.bias", "layer1.blocks.14.mlp.mlp.0.weight", "layer1.blocks.14.mlp.mlp.0.bias", "layer1.blocks.14.mlp.mlp.2.weight", "layer1.blocks.14.mlp.mlp.2.bias", "layer1.blocks.15.norm1.weight", "layer1.blocks.15.norm1.bias", "layer1.blocks.15.norm1.meta1.weight", "layer1.blocks.15.norm1.meta1.bias", "layer1.blocks.15.norm1.meta2.weight", "layer1.blocks.15.norm1.meta2.bias", "layer1.blocks.15.attn.conv.weight", "layer1.blocks.15.attn.conv.bias", "layer1.blocks.15.attn.V.weight", "layer1.blocks.15.attn.V.bias", "layer1.blocks.15.attn.proj.weight", "layer1.blocks.15.attn.proj.bias", "layer1.blocks.15.attn.QK.weight", "layer1.blocks.15.attn.QK.bias", "layer1.blocks.15.attn.attn.relative_positions", "layer1.blocks.15.attn.attn.meta.0.weight", "layer1.blocks.15.attn.attn.meta.0.bias", "layer1.blocks.15.attn.attn.meta.2.weight", "layer1.blocks.15.attn.attn.meta.2.bias", "layer1.blocks.15.mlp.mlp.0.weight", "layer1.blocks.15.mlp.mlp.0.bias", "layer1.blocks.15.mlp.mlp.2.weight", "layer1.blocks.15.mlp.mlp.2.bias", "layer2.blocks.8.norm1.weight", "layer2.blocks.8.norm1.bias", "layer2.blocks.8.norm1.meta1.weight", "layer2.blocks.8.norm1.meta1.bias", "layer2.blocks.8.norm1.meta2.weight", "layer2.blocks.8.norm1.meta2.bias", "layer2.blocks.8.attn.conv.weight", "layer2.blocks.8.attn.conv.bias", "layer2.blocks.8.attn.V.weight", "layer2.blocks.8.attn.V.bias", "layer2.blocks.8.attn.proj.weight", "layer2.blocks.8.attn.proj.bias", "layer2.blocks.8.attn.QK.weight", "layer2.blocks.8.attn.QK.bias", "layer2.blocks.8.attn.attn.relative_positions", "layer2.blocks.8.attn.attn.meta.0.weight", "layer2.blocks.8.attn.attn.meta.0.bias", "layer2.blocks.8.attn.attn.meta.2.weight", "layer2.blocks.8.attn.attn.meta.2.bias", "layer2.blocks.8.mlp.mlp.0.weight", "layer2.blocks.8.mlp.mlp.0.bias", "layer2.blocks.8.mlp.mlp.2.weight", "layer2.blocks.8.mlp.mlp.2.bias", "layer2.blocks.9.norm1.weight", "layer2.blocks.9.norm1.bias", "layer2.blocks.9.norm1.meta1.weight", "layer2.blocks.9.norm1.meta1.bias", "layer2.blocks.9.norm1.meta2.weight", "layer2.blocks.9.norm1.meta2.bias", "layer2.blocks.9.attn.conv.weight", "layer2.blocks.9.attn.conv.bias", "layer2.blocks.9.attn.V.weight", "layer2.blocks.9.attn.V.bias", "layer2.blocks.9.attn.proj.weight", "layer2.blocks.9.attn.proj.bias", "layer2.blocks.9.attn.QK.weight", "layer2.blocks.9.attn.QK.bias", "layer2.blocks.9.attn.attn.relative_positions", "layer2.blocks.9.attn.attn.meta.0.weight", "layer2.blocks.9.attn.attn.meta.0.bias", "layer2.blocks.9.attn.attn.meta.2.weight", "layer2.blocks.9.attn.attn.meta.2.bias", "layer2.blocks.9.mlp.mlp.0.weight", "layer2.blocks.9.mlp.mlp.0.bias", "layer2.blocks.9.mlp.mlp.2.weight", "layer2.blocks.9.mlp.mlp.2.bias", "layer2.blocks.10.norm1.weight", "layer2.blocks.10.norm1.bias", "layer2.blocks.10.norm1.meta1.weight", "layer2.blocks.10.norm1.meta1.bias", "layer2.blocks.10.norm1.meta2.weight", "layer2.blocks.10.norm1.meta2.bias", "layer2.blocks.10.attn.conv.weight", "layer2.blocks.10.attn.conv.bias", "layer2.blocks.10.attn.V.weight", "layer2.blocks.10.attn.V.bias", "layer2.blocks.10.attn.proj.weight", "layer2.blocks.10.attn.proj.bias", "layer2.blocks.10.attn.QK.weight", "layer2.blocks.10.attn.QK.bias", "layer2.blocks.10.attn.attn.relative_positions", "layer2.blocks.10.attn.attn.meta.0.weight", "layer2.blocks.10.attn.attn.meta.0.bias", "layer2.blocks.10.attn.attn.meta.2.weight", "layer2.blocks.10.attn.attn.meta.2.bias", "layer2.blocks.10.mlp.mlp.0.weight", "layer2.blocks.10.mlp.mlp.0.bias", "layer2.blocks.10.mlp.mlp.2.weight", "layer2.blocks.10.mlp.mlp.2.bias", "layer2.blocks.11.norm1.weight", "layer2.blocks.11.norm1.bias", "layer2.blocks.11.norm1.meta1.weight", "layer2.blocks.11.norm1.meta1.bias", "layer2.blocks.11.norm1.meta2.weight", "layer2.blocks.11.norm1.meta2.bias", "layer2.blocks.11.attn.conv.weight", "layer2.blocks.11.attn.conv.bias", "layer2.blocks.11.attn.V.weight", "layer2.blocks.11.attn.V.bias", "layer2.blocks.11.attn.proj.weight", "layer2.blocks.11.attn.proj.bias", "layer2.blocks.11.attn.QK.weight", "layer2.blocks.11.attn.QK.bias", "layer2.blocks.11.attn.attn.relative_positions", "layer2.blocks.11.attn.attn.meta.0.weight", "layer2.blocks.11.attn.attn.meta.0.bias", "layer2.blocks.11.attn.attn.meta.2.weight", "layer2.blocks.11.attn.attn.meta.2.bias", "layer2.blocks.11.mlp.mlp.0.weight", "layer2.blocks.11.mlp.mlp.0.bias", "layer2.blocks.11.mlp.mlp.2.weight", "layer2.blocks.11.mlp.mlp.2.bias", "layer2.blocks.12.norm1.weight", "layer2.blocks.12.norm1.bias", "layer2.blocks.12.norm1.meta1.weight", "layer2.blocks.12.norm1.meta1.bias", "layer2.blocks.12.norm1.meta2.weight", "layer2.blocks.12.norm1.meta2.bias", "layer2.blocks.12.attn.conv.weight", "layer2.blocks.12.attn.conv.bias", "layer2.blocks.12.attn.V.weight", "layer2.blocks.12.attn.V.bias", "layer2.blocks.12.attn.proj.weight", "layer2.blocks.12.attn.proj.bias", "layer2.blocks.12.attn.QK.weight", "layer2.blocks.12.attn.QK.bias", "layer2.blocks.12.attn.attn.relative_positions", "layer2.blocks.12.attn.attn.meta.0.weight", "layer2.blocks.12.attn.attn.meta.0.bias", "layer2.blocks.12.attn.attn.meta.2.weight", "layer2.blocks.12.attn.attn.meta.2.bias", "layer2.blocks.12.mlp.mlp.0.weight", "layer2.blocks.12.mlp.mlp.0.bias", "layer2.blocks.12.mlp.mlp.2.weight", "layer2.blocks.12.mlp.mlp.2.bias", "layer2.blocks.13.norm1.weight", "layer2.blocks.13.norm1.bias", "layer2.blocks.13.norm1.meta1.weight", "layer2.blocks.13.norm1.meta1.bias", "layer2.blocks.13.norm1.meta2.weight", "layer2.blocks.13.norm1.meta2.bias", "layer2.blocks.13.attn.conv.weight", "layer2.blocks.13.attn.conv.bias", "layer2.blocks.13.attn.V.weight", "layer2.blocks.13.attn.V.bias", "layer2.blocks.13.attn.proj.weight", "layer2.blocks.13.attn.proj.bias", "layer2.blocks.13.attn.QK.weight", "layer2.blocks.13.attn.QK.bias", "layer2.blocks.13.attn.attn.relative_positions", "layer2.blocks.13.attn.attn.meta.0.weight", "layer2.blocks.13.attn.attn.meta.0.bias", "layer2.blocks.13.attn.attn.meta.2.weight", "layer2.blocks.13.attn.attn.meta.2.bias", "layer2.blocks.13.mlp.mlp.0.weight", "layer2.blocks.13.mlp.mlp.0.bias", "layer2.blocks.13.mlp.mlp.2.weight", "layer2.blocks.13.mlp.mlp.2.bias", "layer2.blocks.14.norm1.weight", "layer2.blocks.14.norm1.bias", "layer2.blocks.14.norm1.meta1.weight", "layer2.blocks.14.norm1.meta1.bias", "layer2.blocks.14.norm1.meta2.weight", "layer2.blocks.14.norm1.meta2.bias", "layer2.blocks.14.attn.conv.weight", "layer2.blocks.14.attn.conv.bias", "layer2.blocks.14.attn.V.weight", "layer2.blocks.14.attn.V.bias", "layer2.blocks.14.attn.proj.weight", "layer2.blocks.14.attn.proj.bias", "layer2.blocks.14.attn.QK.weight", "layer2.blocks.14.attn.QK.bias", "layer2.blocks.14.attn.attn.relative_positions", "layer2.blocks.14.attn.attn.meta.0.weight", "layer2.blocks.14.attn.attn.meta.0.bias", "layer2.blocks.14.attn.attn.meta.2.weight", "layer2.blocks.14.attn.attn.meta.2.bias", "layer2.blocks.14.mlp.mlp.0.weight", "layer2.blocks.14.mlp.mlp.0.bias", "layer2.blocks.14.mlp.mlp.2.weight", "layer2.blocks.14.mlp.mlp.2.bias", "layer2.blocks.15.norm1.weight", "layer2.blocks.15.norm1.bias", "layer2.blocks.15.norm1.meta1.weight", "layer2.blocks.15.norm1.meta1.bias", "layer2.blocks.15.norm1.meta2.weight", "layer2.blocks.15.norm1.meta2.bias", "layer2.blocks.15.attn.conv.weight", "layer2.blocks.15.attn.conv.bias", "layer2.blocks.15.attn.V.weight", "layer2.blocks.15.attn.V.bias", "layer2.blocks.15.attn.proj.weight", "layer2.blocks.15.attn.proj.bias", "layer2.blocks.15.attn.QK.weight", "layer2.blocks.15.attn.QK.bias", "layer2.blocks.15.attn.attn.relative_positions", "layer2.blocks.15.attn.attn.meta.0.weight", "layer2.blocks.15.attn.attn.meta.0.bias", "layer2.blocks.15.attn.attn.meta.2.weight", "layer2.blocks.15.attn.attn.meta.2.bias", "layer2.blocks.15.mlp.mlp.0.weight", "layer2.blocks.15.mlp.mlp.0.bias", "layer2.blocks.15.mlp.mlp.2.weight", "layer2.blocks.15.mlp.mlp.2.bias", "layer3.blocks.8.norm1.weight", "layer3.blocks.8.norm1.bias", "layer3.blocks.8.norm1.meta1.weight", "layer3.blocks.8.norm1.meta1.bias", "layer3.blocks.8.norm1.meta2.weight", "layer3.blocks.8.norm1.meta2.bias", "layer3.blocks.8.attn.conv.weight", "layer3.blocks.8.attn.conv.bias", "layer3.blocks.8.attn.V.weight", "layer3.blocks.8.attn.V.bias", "layer3.blocks.8.attn.proj.weight", "layer3.blocks.8.attn.proj.bias", "layer3.blocks.8.attn.QK.weight", "layer3.blocks.8.attn.QK.bias", "layer3.blocks.8.attn.attn.relative_positions", "layer3.blocks.8.attn.attn.meta.0.weight", "layer3.blocks.8.attn.attn.meta.0.bias", "layer3.blocks.8.attn.attn.meta.2.weight", "layer3.blocks.8.attn.attn.meta.2.bias", "layer3.blocks.8.mlp.mlp.0.weight", "layer3.blocks.8.mlp.mlp.0.bias", "layer3.blocks.8.mlp.mlp.2.weight", "layer3.blocks.8.mlp.mlp.2.bias", "layer3.blocks.9.norm1.weight", "layer3.blocks.9.norm1.bias", "layer3.blocks.9.norm1.meta1.weight", "layer3.blocks.9.norm1.meta1.bias", "layer3.blocks.9.norm1.meta2.weight", "layer3.blocks.9.norm1.meta2.bias", "layer3.blocks.9.attn.conv.weight", "layer3.blocks.9.attn.conv.bias", "layer3.blocks.9.attn.V.weight", "layer3.blocks.9.attn.V.bias", "layer3.blocks.9.attn.proj.weight", "layer3.blocks.9.attn.proj.bias", "layer3.blocks.9.attn.QK.weight", "layer3.blocks.9.attn.QK.bias", "layer3.blocks.9.attn.attn.relative_positions", "layer3.blocks.9.attn.attn.meta.0.weight", "layer3.blocks.9.attn.attn.meta.0.bias", "layer3.blocks.9.attn.attn.meta.2.weight", "layer3.blocks.9.attn.attn.meta.2.bias", "layer3.blocks.9.mlp.mlp.0.weight", "layer3.blocks.9.mlp.mlp.0.bias", "layer3.blocks.9.mlp.mlp.2.weight", "layer3.blocks.9.mlp.mlp.2.bias", "layer3.blocks.10.norm1.weight", "layer3.blocks.10.norm1.bias", "layer3.blocks.10.norm1.meta1.weight", "layer3.blocks.10.norm1.meta1.bias", "layer3.blocks.10.norm1.meta2.weight", "layer3.blocks.10.norm1.meta2.bias", "layer3.blocks.10.attn.conv.weight", "layer3.blocks.10.attn.conv.bias", "layer3.blocks.10.attn.V.weight", "layer3.blocks.10.attn.V.bias", "layer3.blocks.10.attn.proj.weight", "layer3.blocks.10.attn.proj.bias", "layer3.blocks.10.attn.QK.weight", "layer3.blocks.10.attn.QK.bias", "layer3.blocks.10.attn.attn.relative_positions", "layer3.blocks.10.attn.attn.meta.0.weight", "layer3.blocks.10.attn.attn.meta.0.bias", "layer3.blocks.10.attn.attn.meta.2.weight", "layer3.blocks.10.attn.attn.meta.2.bias", "layer3.blocks.10.mlp.mlp.0.weight", "layer3.blocks.10.mlp.mlp.0.bias", "layer3.blocks.10.mlp.mlp.2.weight", "layer3.blocks.10.mlp.mlp.2.bias", "layer3.blocks.11.norm1.weight", "layer3.blocks.11.norm1.bias", "layer3.blocks.11.norm1.meta1.weight", "layer3.blocks.11.norm1.meta1.bias", "layer3.blocks.11.norm1.meta2.weight", "layer3.blocks.11.norm1.meta2.bias", "layer3.blocks.11.attn.conv.weight", "layer3.blocks.11.attn.conv.bias", "layer3.blocks.11.attn.V.weight", "layer3.blocks.11.attn.V.bias", "layer3.blocks.11.attn.proj.weight", "layer3.blocks.11.attn.proj.bias", "layer3.blocks.11.attn.QK.weight", "layer3.blocks.11.attn.QK.bias", "layer3.blocks.11.attn.attn.relative_positions", "layer3.blocks.11.attn.attn.meta.0.weight", "layer3.blocks.11.attn.attn.meta.0.bias", "layer3.blocks.11.attn.attn.meta.2.weight", "layer3.blocks.11.attn.attn.meta.2.bias", "layer3.blocks.11.mlp.mlp.0.weight", "layer3.blocks.11.mlp.mlp.0.bias", "layer3.blocks.11.mlp.mlp.2.weight", "layer3.blocks.11.mlp.mlp.2.bias", "layer3.blocks.12.norm1.weight", "layer3.blocks.12.norm1.bias", "layer3.blocks.12.norm1.meta1.weight", "layer3.blocks.12.norm1.meta1.bias", "layer3.blocks.12.norm1.meta2.weight", "layer3.blocks.12.norm1.meta2.bias", "layer3.blocks.12.attn.conv.weight", "layer3.blocks.12.attn.conv.bias", "layer3.blocks.12.attn.V.weight", "layer3.blocks.12.attn.V.bias", "layer3.blocks.12.attn.proj.weight", "layer3.blocks.12.attn.proj.bias", "layer3.blocks.12.attn.QK.weight", "layer3.blocks.12.attn.QK.bias", "layer3.blocks.12.attn.attn.relative_positions", "layer3.blocks.12.attn.attn.meta.0.weight", "layer3.blocks.12.attn.attn.meta.0.bias", "layer3.blocks.12.attn.attn.meta.2.weight", "layer3.blocks.12.attn.attn.meta.2.bias", "layer3.blocks.12.mlp.mlp.0.weight", "layer3.blocks.12.mlp.mlp.0.bias", "layer3.blocks.12.mlp.mlp.2.weight", "layer3.blocks.12.mlp.mlp.2.bias", "layer3.blocks.13.norm1.weight", "layer3.blocks.13.norm1.bias", "layer3.blocks.13.norm1.meta1.weight", "layer3.blocks.13.norm1.meta1.bias", "layer3.blocks.13.norm1.meta2.weight", "layer3.blocks.13.norm1.meta2.bias", "layer3.blocks.13.attn.conv.weight", "layer3.blocks.13.attn.conv.bias", "layer3.blocks.13.attn.V.weight", "layer3.blocks.13.attn.V.bias", "layer3.blocks.13.attn.proj.weight", "layer3.blocks.13.attn.proj.bias", "layer3.blocks.13.attn.QK.weight", "layer3.blocks.13.attn.QK.bias", "layer3.blocks.13.attn.attn.relative_positions", "layer3.blocks.13.attn.attn.meta.0.weight", "layer3.blocks.13.attn.attn.meta.0.bias", "layer3.blocks.13.attn.attn.meta.2.weight", "layer3.blocks.13.attn.attn.meta.2.bias", "layer3.blocks.13.mlp.mlp.0.weight", "layer3.blocks.13.mlp.mlp.0.bias", "layer3.blocks.13.mlp.mlp.2.weight", "layer3.blocks.13.mlp.mlp.2.bias", "layer3.blocks.14.norm1.weight", "layer3.blocks.14.norm1.bias", "layer3.blocks.14.norm1.meta1.weight", "layer3.blocks.14.norm1.meta1.bias", "layer3.blocks.14.norm1.meta2.weight", "layer3.blocks.14.norm1.meta2.bias", "layer3.blocks.14.attn.conv.weight", "layer3.blocks.14.attn.conv.bias", "layer3.blocks.14.attn.V.weight", "layer3.blocks.14.attn.V.bias", "layer3.blocks.14.attn.proj.weight", "layer3.blocks.14.attn.proj.bias", "layer3.blocks.14.attn.QK.weight", "layer3.blocks.14.attn.QK.bias", "layer3.blocks.14.attn.attn.relative_positions", "layer3.blocks.14.attn.attn.meta.0.weight", "layer3.blocks.14.attn.attn.meta.0.bias", "layer3.blocks.14.attn.attn.meta.2.weight", "layer3.blocks.14.attn.attn.meta.2.bias", "layer3.blocks.14.mlp.mlp.0.weight", "layer3.blocks.14.mlp.mlp.0.bias", "layer3.blocks.14.mlp.mlp.2.weight", "layer3.blocks.14.mlp.mlp.2.bias", "layer3.blocks.15.norm1.weight", "layer3.blocks.15.norm1.bias", "layer3.blocks.15.norm1.meta1.weight", "layer3.blocks.15.norm1.meta1.bias", "layer3.blocks.15.norm1.meta2.weight", "layer3.blocks.15.norm1.meta2.bias", "layer3.blocks.15.attn.conv.weight", "layer3.blocks.15.attn.conv.bias", "layer3.blocks.15.attn.V.weight", "layer3.blocks.15.attn.V.bias", "layer3.blocks.15.attn.proj.weight", "layer3.blocks.15.attn.proj.bias", "layer3.blocks.15.attn.QK.weight", "layer3.blocks.15.attn.QK.bias", "layer3.blocks.15.attn.attn.relative_positions", "layer3.blocks.15.attn.attn.meta.0.weight", "layer3.blocks.15.attn.attn.meta.0.bias", "layer3.blocks.15.attn.attn.meta.2.weight", "layer3.blocks.15.attn.attn.meta.2.bias", "layer3.blocks.15.mlp.mlp.0.weight", "layer3.blocks.15.mlp.mlp.0.bias", "layer3.blocks.15.mlp.mlp.2.weight", "layer3.blocks.15.mlp.mlp.2.bias", "layer4.blocks.4.attn.conv.weight", "layer4.blocks.4.attn.conv.bias", "layer4.blocks.4.attn.V.weight", "layer4.blocks.4.attn.V.bias", "layer4.blocks.4.attn.proj.weight", "layer4.blocks.4.attn.proj.bias", "layer4.blocks.4.mlp.mlp.0.weight", "layer4.blocks.4.mlp.mlp.0.bias", "layer4.blocks.4.mlp.mlp.2.weight", "layer4.blocks.4.mlp.mlp.2.bias", "layer4.blocks.5.attn.conv.weight", "layer4.blocks.5.attn.conv.bias", "layer4.blocks.5.attn.V.weight", "layer4.blocks.5.attn.V.bias", "layer4.blocks.5.attn.proj.weight", "layer4.blocks.5.attn.proj.bias", "layer4.blocks.5.mlp.mlp.0.weight", "layer4.blocks.5.mlp.mlp.0.bias", "layer4.blocks.5.mlp.mlp.2.weight", "layer4.blocks.5.mlp.mlp.2.bias", "layer4.blocks.6.attn.conv.weight", "layer4.blocks.6.attn.conv.bias", "layer4.blocks.6.attn.V.weight", "layer4.blocks.6.attn.V.bias", "layer4.blocks.6.attn.proj.weight", "layer4.blocks.6.attn.proj.bias", "layer4.blocks.6.mlp.mlp.0.weight", "layer4.blocks.6.mlp.mlp.0.bias", "layer4.blocks.6.mlp.mlp.2.weight", "layer4.blocks.6.mlp.mlp.2.bias", "layer4.blocks.7.attn.conv.weight", "layer4.blocks.7.attn.conv.bias", "layer4.blocks.7.attn.V.weight", "layer4.blocks.7.attn.V.bias", "layer4.blocks.7.attn.proj.weight", "layer4.blocks.7.attn.proj.bias", "layer4.blocks.7.mlp.mlp.0.weight", "layer4.blocks.7.mlp.mlp.0.bias", "layer4.blocks.7.mlp.mlp.2.weight", "layer4.blocks.7.mlp.mlp.2.bias", "layer5.blocks.4.attn.conv.weight", "layer5.blocks.4.attn.conv.bias", "layer5.blocks.4.attn.V.weight", "layer5.blocks.4.attn.V.bias", "layer5.blocks.4.attn.proj.weight", "layer5.blocks.4.attn.proj.bias", "layer5.blocks.4.mlp.mlp.0.weight", "layer5.blocks.4.mlp.mlp.0.bias", "layer5.blocks.4.mlp.mlp.2.weight", "layer5.blocks.4.mlp.mlp.2.bias", "layer5.blocks.5.attn.conv.weight", "layer5.blocks.5.attn.conv.bias", "layer5.blocks.5.attn.V.weight", "layer5.blocks.5.attn.V.bias", "layer5.blocks.5.attn.proj.weight", "layer5.blocks.5.attn.proj.bias", "layer5.blocks.5.mlp.mlp.0.weight", "layer5.blocks.5.mlp.mlp.0.bias", "layer5.blocks.5.mlp.mlp.2.weight", "layer5.blocks.5.mlp.mlp.2.bias", "layer5.blocks.6.attn.conv.weight", "layer5.blocks.6.attn.conv.bias", "layer5.blocks.6.attn.V.weight", "layer5.blocks.6.attn.V.bias", "layer5.blocks.6.attn.proj.weight", "layer5.blocks.6.attn.proj.bias", "layer5.blocks.6.mlp.mlp.0.weight", "layer5.blocks.6.mlp.mlp.0.bias", "layer5.blocks.6.mlp.mlp.2.weight", "layer5.blocks.6.mlp.mlp.2.bias", "layer5.blocks.7.attn.conv.weight", "layer5.blocks.7.attn.conv.bias", "layer5.blocks.7.attn.V.weight", "layer5.blocks.7.attn.V.bias", "layer5.blocks.7.attn.proj.weight", "layer5.blocks.7.attn.proj.bias", "layer5.blocks.7.mlp.mlp.0.weight", "layer5.blocks.7.mlp.mlp.0.bias", "layer5.blocks.7.mlp.mlp.2.weight", "layer5.blocks.7.mlp.mlp.2.bias".

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant