cond_stage_model.model.token_embedding.weight#torch.Size([49408, 1024])#torch.float32
cond_stage_model.model.ln_final.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.ln_final.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.positional_embedding#torch.Size([77, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.0.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.0.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.0.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.0.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.0.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.0.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.0.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.0.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.0.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.0.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.0.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.0.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.1.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.1.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.1.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.1.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.1.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.1.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.1.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.1.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.1.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.1.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.1.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.1.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.10.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.10.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.10.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.10.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.10.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.10.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.10.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.10.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.10.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.10.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.10.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.10.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.11.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.11.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.11.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.11.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.11.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.11.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.11.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.11.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.11.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.11.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.11.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.11.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.12.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.12.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.12.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.12.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.12.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.12.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.12.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.12.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.12.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.12.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.12.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.12.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.13.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.13.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.13.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.13.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.13.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.13.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.13.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.13.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.13.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.13.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.13.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.13.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.14.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.14.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.14.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.14.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.14.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.14.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.14.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.14.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.14.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.14.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.14.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.14.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.15.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.15.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.15.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.15.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.15.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.15.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.15.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.15.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.15.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.15.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.15.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.15.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.16.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.16.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.16.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.16.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.16.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.16.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.16.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.16.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.16.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.16.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.16.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.16.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.17.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.17.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.17.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.17.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.17.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.17.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.17.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.17.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.17.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.17.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.17.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.17.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.18.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.18.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.18.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.18.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.18.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.18.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.18.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.18.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.18.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.18.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.18.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.18.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.19.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.19.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.19.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.19.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.19.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.19.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.19.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.19.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.19.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.19.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.19.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.19.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.2.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.2.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.2.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.2.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.2.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.2.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.2.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.2.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.2.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.2.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.2.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.2.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.20.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.20.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.20.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.20.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.20.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.20.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.20.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.20.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.20.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.20.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.20.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.20.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.21.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.21.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.21.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.21.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.21.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.21.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.21.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.21.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.21.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.21.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.21.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.21.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.22.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.22.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.22.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.22.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.22.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.22.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.22.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.22.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.22.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.22.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.22.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.22.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.3.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.3.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.3.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.3.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.3.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.3.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.3.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.3.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.3.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.3.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.3.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.3.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.4.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.4.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.4.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.4.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.4.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.4.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.4.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.4.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.4.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.4.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.4.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.4.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.5.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.5.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.5.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.5.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.5.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.5.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.5.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.5.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.5.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.5.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.5.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.5.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.6.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.6.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.6.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.6.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.6.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.6.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.6.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.6.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.6.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.6.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.6.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.6.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.7.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.7.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.7.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.7.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.7.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.7.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.7.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.7.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.7.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.7.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.7.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.7.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.8.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.8.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.8.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.8.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.8.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.8.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.8.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.8.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.8.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.8.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.8.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.8.ln_2.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.9.attn.in_proj_bias#torch.Size([3072])#torch.float32
cond_stage_model.model.transformer.resblocks.9.attn.in_proj_weight#torch.Size([3072, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.9.attn.out_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.9.attn.out_proj.weight#torch.Size([1024, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.9.mlp.c_fc.bias#torch.Size([4096])#torch.float32
cond_stage_model.model.transformer.resblocks.9.mlp.c_fc.weight#torch.Size([4096, 1024])#torch.float32
cond_stage_model.model.transformer.resblocks.9.mlp.c_proj.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.9.mlp.c_proj.weight#torch.Size([1024, 4096])#torch.float32
cond_stage_model.model.transformer.resblocks.9.ln_1.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.9.ln_1.weight#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.9.ln_2.bias#torch.Size([1024])#torch.float32
cond_stage_model.model.transformer.resblocks.9.ln_2.weight#torch.Size([1024])#torch.float32
first_stage_model.decoder.conv_in.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.conv_in.weight#torch.Size([512, 4, 3, 3])#torch.float32
first_stage_model.decoder.conv_out.bias#torch.Size([3])#torch.float32
first_stage_model.decoder.conv_out.weight#torch.Size([3, 128, 3, 3])#torch.float32
first_stage_model.decoder.mid.attn_1.k.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.mid.attn_1.k.weight#torch.Size([512, 512, 1, 1])#torch.float32
first_stage_model.decoder.mid.attn_1.norm.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.mid.attn_1.norm.weight#torch.Size([512])#torch.float32
first_stage_model.decoder.mid.attn_1.proj_out.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.mid.attn_1.proj_out.weight#torch.Size([512, 512, 1, 1])#torch.float32
first_stage_model.decoder.mid.attn_1.q.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.mid.attn_1.q.weight#torch.Size([512, 512, 1, 1])#torch.float32
first_stage_model.decoder.mid.attn_1.v.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.mid.attn_1.v.weight#torch.Size([512, 512, 1, 1])#torch.float32
first_stage_model.decoder.mid.block_1.conv1.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.mid.block_1.conv1.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.decoder.mid.block_1.conv2.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.mid.block_1.conv2.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.decoder.mid.block_1.norm1.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.mid.block_1.norm1.weight#torch.Size([512])#torch.float32
first_stage_model.decoder.mid.block_1.norm2.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.mid.block_1.norm2.weight#torch.Size([512])#torch.float32
first_stage_model.decoder.mid.block_2.conv1.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.mid.block_2.conv1.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.decoder.mid.block_2.conv2.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.mid.block_2.conv2.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.decoder.mid.block_2.norm1.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.mid.block_2.norm1.weight#torch.Size([512])#torch.float32
first_stage_model.decoder.mid.block_2.norm2.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.mid.block_2.norm2.weight#torch.Size([512])#torch.float32
first_stage_model.decoder.norm_out.bias#torch.Size([128])#torch.float32
first_stage_model.decoder.norm_out.weight#torch.Size([128])#torch.float32
first_stage_model.decoder.up.0.block.0.conv1.bias#torch.Size([128])#torch.float32
first_stage_model.decoder.up.0.block.0.conv1.weight#torch.Size([128, 256, 3, 3])#torch.float32
first_stage_model.decoder.up.0.block.0.conv2.bias#torch.Size([128])#torch.float32
first_stage_model.decoder.up.0.block.0.conv2.weight#torch.Size([128, 128, 3, 3])#torch.float32
first_stage_model.decoder.up.0.block.0.nin_shortcut.bias#torch.Size([128])#torch.float32
first_stage_model.decoder.up.0.block.0.nin_shortcut.weight#torch.Size([128, 256, 1, 1])#torch.float32
first_stage_model.decoder.up.0.block.0.norm1.bias#torch.Size([256])#torch.float32
first_stage_model.decoder.up.0.block.0.norm1.weight#torch.Size([256])#torch.float32
first_stage_model.decoder.up.0.block.0.norm2.bias#torch.Size([128])#torch.float32
first_stage_model.decoder.up.0.block.0.norm2.weight#torch.Size([128])#torch.float32
first_stage_model.decoder.up.0.block.1.conv1.bias#torch.Size([128])#torch.float32
first_stage_model.decoder.up.0.block.1.conv1.weight#torch.Size([128, 128, 3, 3])#torch.float32
first_stage_model.decoder.up.0.block.1.conv2.bias#torch.Size([128])#torch.float32
first_stage_model.decoder.up.0.block.1.conv2.weight#torch.Size([128, 128, 3, 3])#torch.float32
first_stage_model.decoder.up.0.block.1.norm1.bias#torch.Size([128])#torch.float32
first_stage_model.decoder.up.0.block.1.norm1.weight#torch.Size([128])#torch.float32
first_stage_model.decoder.up.0.block.1.norm2.bias#torch.Size([128])#torch.float32
first_stage_model.decoder.up.0.block.1.norm2.weight#torch.Size([128])#torch.float32
first_stage_model.decoder.up.0.block.2.conv1.bias#torch.Size([128])#torch.float32
first_stage_model.decoder.up.0.block.2.conv1.weight#torch.Size([128, 128, 3, 3])#torch.float32
first_stage_model.decoder.up.0.block.2.conv2.bias#torch.Size([128])#torch.float32
first_stage_model.decoder.up.0.block.2.conv2.weight#torch.Size([128, 128, 3, 3])#torch.float32
first_stage_model.decoder.up.0.block.2.norm1.bias#torch.Size([128])#torch.float32
first_stage_model.decoder.up.0.block.2.norm1.weight#torch.Size([128])#torch.float32
first_stage_model.decoder.up.0.block.2.norm2.bias#torch.Size([128])#torch.float32
first_stage_model.decoder.up.0.block.2.norm2.weight#torch.Size([128])#torch.float32
first_stage_model.decoder.up.1.block.0.conv1.bias#torch.Size([256])#torch.float32
first_stage_model.decoder.up.1.block.0.conv1.weight#torch.Size([256, 512, 3, 3])#torch.float32
first_stage_model.decoder.up.1.block.0.conv2.bias#torch.Size([256])#torch.float32
first_stage_model.decoder.up.1.block.0.conv2.weight#torch.Size([256, 256, 3, 3])#torch.float32
first_stage_model.decoder.up.1.block.0.nin_shortcut.bias#torch.Size([256])#torch.float32
first_stage_model.decoder.up.1.block.0.nin_shortcut.weight#torch.Size([256, 512, 1, 1])#torch.float32
first_stage_model.decoder.up.1.block.0.norm1.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.1.block.0.norm1.weight#torch.Size([512])#torch.float32
first_stage_model.decoder.up.1.block.0.norm2.bias#torch.Size([256])#torch.float32
first_stage_model.decoder.up.1.block.0.norm2.weight#torch.Size([256])#torch.float32
first_stage_model.decoder.up.1.block.1.conv1.bias#torch.Size([256])#torch.float32
first_stage_model.decoder.up.1.block.1.conv1.weight#torch.Size([256, 256, 3, 3])#torch.float32
first_stage_model.decoder.up.1.block.1.conv2.bias#torch.Size([256])#torch.float32
first_stage_model.decoder.up.1.block.1.conv2.weight#torch.Size([256, 256, 3, 3])#torch.float32
first_stage_model.decoder.up.1.block.1.norm1.bias#torch.Size([256])#torch.float32
first_stage_model.decoder.up.1.block.1.norm1.weight#torch.Size([256])#torch.float32
first_stage_model.decoder.up.1.block.1.norm2.bias#torch.Size([256])#torch.float32
first_stage_model.decoder.up.1.block.1.norm2.weight#torch.Size([256])#torch.float32
first_stage_model.decoder.up.1.block.2.conv1.bias#torch.Size([256])#torch.float32
first_stage_model.decoder.up.1.block.2.conv1.weight#torch.Size([256, 256, 3, 3])#torch.float32
first_stage_model.decoder.up.1.block.2.conv2.bias#torch.Size([256])#torch.float32
first_stage_model.decoder.up.1.block.2.conv2.weight#torch.Size([256, 256, 3, 3])#torch.float32
first_stage_model.decoder.up.1.block.2.norm1.bias#torch.Size([256])#torch.float32
first_stage_model.decoder.up.1.block.2.norm1.weight#torch.Size([256])#torch.float32
first_stage_model.decoder.up.1.block.2.norm2.bias#torch.Size([256])#torch.float32
first_stage_model.decoder.up.1.block.2.norm2.weight#torch.Size([256])#torch.float32
first_stage_model.decoder.up.1.upsample.conv.bias#torch.Size([256])#torch.float32
first_stage_model.decoder.up.1.upsample.conv.weight#torch.Size([256, 256, 3, 3])#torch.float32
first_stage_model.decoder.up.2.block.0.conv1.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.block.0.conv1.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.decoder.up.2.block.0.conv2.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.block.0.conv2.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.decoder.up.2.block.0.norm1.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.block.0.norm1.weight#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.block.0.norm2.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.block.0.norm2.weight#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.block.1.conv1.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.block.1.conv1.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.decoder.up.2.block.1.conv2.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.block.1.conv2.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.decoder.up.2.block.1.norm1.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.block.1.norm1.weight#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.block.1.norm2.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.block.1.norm2.weight#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.block.2.conv1.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.block.2.conv1.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.decoder.up.2.block.2.conv2.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.block.2.conv2.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.decoder.up.2.block.2.norm1.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.block.2.norm1.weight#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.block.2.norm2.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.block.2.norm2.weight#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.upsample.conv.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.2.upsample.conv.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.decoder.up.3.block.0.conv1.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.block.0.conv1.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.decoder.up.3.block.0.conv2.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.block.0.conv2.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.decoder.up.3.block.0.norm1.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.block.0.norm1.weight#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.block.0.norm2.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.block.0.norm2.weight#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.block.1.conv1.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.block.1.conv1.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.decoder.up.3.block.1.conv2.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.block.1.conv2.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.decoder.up.3.block.1.norm1.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.block.1.norm1.weight#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.block.1.norm2.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.block.1.norm2.weight#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.block.2.conv1.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.block.2.conv1.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.decoder.up.3.block.2.conv2.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.block.2.conv2.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.decoder.up.3.block.2.norm1.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.block.2.norm1.weight#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.block.2.norm2.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.block.2.norm2.weight#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.upsample.conv.bias#torch.Size([512])#torch.float32
first_stage_model.decoder.up.3.upsample.conv.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.encoder.conv_in.bias#torch.Size([128])#torch.float32
first_stage_model.encoder.conv_in.weight#torch.Size([128, 3, 3, 3])#torch.float32
first_stage_model.encoder.conv_out.bias#torch.Size([8])#torch.float32
first_stage_model.encoder.conv_out.weight#torch.Size([8, 512, 3, 3])#torch.float32
first_stage_model.encoder.down.0.block.0.conv1.bias#torch.Size([128])#torch.float32
first_stage_model.encoder.down.0.block.0.conv1.weight#torch.Size([128, 128, 3, 3])#torch.float32
first_stage_model.encoder.down.0.block.0.conv2.bias#torch.Size([128])#torch.float32
first_stage_model.encoder.down.0.block.0.conv2.weight#torch.Size([128, 128, 3, 3])#torch.float32
first_stage_model.encoder.down.0.block.0.norm1.bias#torch.Size([128])#torch.float32
first_stage_model.encoder.down.0.block.0.norm1.weight#torch.Size([128])#torch.float32
first_stage_model.encoder.down.0.block.0.norm2.bias#torch.Size([128])#torch.float32
first_stage_model.encoder.down.0.block.0.norm2.weight#torch.Size([128])#torch.float32
first_stage_model.encoder.down.0.block.1.conv1.bias#torch.Size([128])#torch.float32
first_stage_model.encoder.down.0.block.1.conv1.weight#torch.Size([128, 128, 3, 3])#torch.float32
first_stage_model.encoder.down.0.block.1.conv2.bias#torch.Size([128])#torch.float32
first_stage_model.encoder.down.0.block.1.conv2.weight#torch.Size([128, 128, 3, 3])#torch.float32
first_stage_model.encoder.down.0.block.1.norm1.bias#torch.Size([128])#torch.float32
first_stage_model.encoder.down.0.block.1.norm1.weight#torch.Size([128])#torch.float32
first_stage_model.encoder.down.0.block.1.norm2.bias#torch.Size([128])#torch.float32
first_stage_model.encoder.down.0.block.1.norm2.weight#torch.Size([128])#torch.float32
first_stage_model.encoder.down.0.downsample.conv.bias#torch.Size([128])#torch.float32
first_stage_model.encoder.down.0.downsample.conv.weight#torch.Size([128, 128, 3, 3])#torch.float32
first_stage_model.encoder.down.1.block.0.conv1.bias#torch.Size([256])#torch.float32
first_stage_model.encoder.down.1.block.0.conv1.weight#torch.Size([256, 128, 3, 3])#torch.float32
first_stage_model.encoder.down.1.block.0.conv2.bias#torch.Size([256])#torch.float32
first_stage_model.encoder.down.1.block.0.conv2.weight#torch.Size([256, 256, 3, 3])#torch.float32
first_stage_model.encoder.down.1.block.0.nin_shortcut.bias#torch.Size([256])#torch.float32
first_stage_model.encoder.down.1.block.0.nin_shortcut.weight#torch.Size([256, 128, 1, 1])#torch.float32
first_stage_model.encoder.down.1.block.0.norm1.bias#torch.Size([128])#torch.float32
first_stage_model.encoder.down.1.block.0.norm1.weight#torch.Size([128])#torch.float32
first_stage_model.encoder.down.1.block.0.norm2.bias#torch.Size([256])#torch.float32
first_stage_model.encoder.down.1.block.0.norm2.weight#torch.Size([256])#torch.float32
first_stage_model.encoder.down.1.block.1.conv1.bias#torch.Size([256])#torch.float32
first_stage_model.encoder.down.1.block.1.conv1.weight#torch.Size([256, 256, 3, 3])#torch.float32
first_stage_model.encoder.down.1.block.1.conv2.bias#torch.Size([256])#torch.float32
first_stage_model.encoder.down.1.block.1.conv2.weight#torch.Size([256, 256, 3, 3])#torch.float32
first_stage_model.encoder.down.1.block.1.norm1.bias#torch.Size([256])#torch.float32
first_stage_model.encoder.down.1.block.1.norm1.weight#torch.Size([256])#torch.float32
first_stage_model.encoder.down.1.block.1.norm2.bias#torch.Size([256])#torch.float32
first_stage_model.encoder.down.1.block.1.norm2.weight#torch.Size([256])#torch.float32
first_stage_model.encoder.down.1.downsample.conv.bias#torch.Size([256])#torch.float32
first_stage_model.encoder.down.1.downsample.conv.weight#torch.Size([256, 256, 3, 3])#torch.float32
first_stage_model.encoder.down.2.block.0.conv1.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.down.2.block.0.conv1.weight#torch.Size([512, 256, 3, 3])#torch.float32
first_stage_model.encoder.down.2.block.0.conv2.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.down.2.block.0.conv2.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.encoder.down.2.block.0.nin_shortcut.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.down.2.block.0.nin_shortcut.weight#torch.Size([512, 256, 1, 1])#torch.float32
first_stage_model.encoder.down.2.block.0.norm1.bias#torch.Size([256])#torch.float32
first_stage_model.encoder.down.2.block.0.norm1.weight#torch.Size([256])#torch.float32
first_stage_model.encoder.down.2.block.0.norm2.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.down.2.block.0.norm2.weight#torch.Size([512])#torch.float32
first_stage_model.encoder.down.2.block.1.conv1.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.down.2.block.1.conv1.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.encoder.down.2.block.1.conv2.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.down.2.block.1.conv2.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.encoder.down.2.block.1.norm1.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.down.2.block.1.norm1.weight#torch.Size([512])#torch.float32
first_stage_model.encoder.down.2.block.1.norm2.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.down.2.block.1.norm2.weight#torch.Size([512])#torch.float32
first_stage_model.encoder.down.2.downsample.conv.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.down.2.downsample.conv.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.encoder.down.3.block.0.conv1.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.down.3.block.0.conv1.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.encoder.down.3.block.0.conv2.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.down.3.block.0.conv2.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.encoder.down.3.block.0.norm1.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.down.3.block.0.norm1.weight#torch.Size([512])#torch.float32
first_stage_model.encoder.down.3.block.0.norm2.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.down.3.block.0.norm2.weight#torch.Size([512])#torch.float32
first_stage_model.encoder.down.3.block.1.conv1.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.down.3.block.1.conv1.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.encoder.down.3.block.1.conv2.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.down.3.block.1.conv2.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.encoder.down.3.block.1.norm1.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.down.3.block.1.norm1.weight#torch.Size([512])#torch.float32
first_stage_model.encoder.down.3.block.1.norm2.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.down.3.block.1.norm2.weight#torch.Size([512])#torch.float32
first_stage_model.encoder.mid.attn_1.k.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.mid.attn_1.k.weight#torch.Size([512, 512, 1, 1])#torch.float32
first_stage_model.encoder.mid.attn_1.norm.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.mid.attn_1.norm.weight#torch.Size([512])#torch.float32
first_stage_model.encoder.mid.attn_1.proj_out.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.mid.attn_1.proj_out.weight#torch.Size([512, 512, 1, 1])#torch.float32
first_stage_model.encoder.mid.attn_1.q.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.mid.attn_1.q.weight#torch.Size([512, 512, 1, 1])#torch.float32
first_stage_model.encoder.mid.attn_1.v.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.mid.attn_1.v.weight#torch.Size([512, 512, 1, 1])#torch.float32
first_stage_model.encoder.mid.block_1.conv1.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.mid.block_1.conv1.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.encoder.mid.block_1.conv2.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.mid.block_1.conv2.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.encoder.mid.block_1.norm1.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.mid.block_1.norm1.weight#torch.Size([512])#torch.float32
first_stage_model.encoder.mid.block_1.norm2.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.mid.block_1.norm2.weight#torch.Size([512])#torch.float32
first_stage_model.encoder.mid.block_2.conv1.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.mid.block_2.conv1.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.encoder.mid.block_2.conv2.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.mid.block_2.conv2.weight#torch.Size([512, 512, 3, 3])#torch.float32
first_stage_model.encoder.mid.block_2.norm1.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.mid.block_2.norm1.weight#torch.Size([512])#torch.float32
first_stage_model.encoder.mid.block_2.norm2.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.mid.block_2.norm2.weight#torch.Size([512])#torch.float32
first_stage_model.encoder.norm_out.bias#torch.Size([512])#torch.float32
first_stage_model.encoder.norm_out.weight#torch.Size([512])#torch.float32
first_stage_model.post_quant_conv.bias#torch.Size([4])#torch.float32
first_stage_model.post_quant_conv.weight#torch.Size([4, 4, 1, 1])#torch.float32
first_stage_model.quant_conv.bias#torch.Size([8])#torch.float32
first_stage_model.quant_conv.weight#torch.Size([8, 8, 1, 1])#torch.float32
model.diffusion_model.input_blocks.0.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.0.0.weight#torch.Size([320, 4, 3, 3])#torch.float32
model.diffusion_model.input_blocks.1.0.emb_layers.1.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.0.emb_layers.1.weight#torch.Size([320, 1280])#torch.float32
model.diffusion_model.input_blocks.1.0.in_layers.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.0.in_layers.0.weight#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.0.in_layers.2.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.0.in_layers.2.weight#torch.Size([320, 320, 3, 3])#torch.float32
model.diffusion_model.input_blocks.1.0.out_layers.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.0.out_layers.0.weight#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.0.out_layers.3.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.0.out_layers.3.weight#torch.Size([320, 320, 3, 3])#torch.float32
model.diffusion_model.input_blocks.1.1.norm.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.1.norm.weight#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.1.proj_in.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.1.proj_in.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.input_blocks.1.1.proj_out.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.1.proj_out.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn1.to_k.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn1.to_out.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn1.to_out.0.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn1.to_q.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn1.to_v.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn2.to_k.weight#torch.Size([320, 1024])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn2.to_out.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn2.to_out.0.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn2.to_q.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn2.to_v.weight#torch.Size([320, 1024])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.ff.net.0.proj.bias#torch.Size([2560])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.ff.net.0.proj.weight#torch.Size([2560, 320])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.ff.net.2.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.ff.net.2.weight#torch.Size([320, 1280])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.norm1.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.norm1.weight#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.norm2.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.norm2.weight#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.norm3.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.1.1.transformer_blocks.0.norm3.weight#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.10.0.emb_layers.1.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.10.0.emb_layers.1.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.10.0.in_layers.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.10.0.in_layers.0.weight#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.10.0.in_layers.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.10.0.in_layers.2.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.input_blocks.10.0.out_layers.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.10.0.out_layers.0.weight#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.10.0.out_layers.3.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.10.0.out_layers.3.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.input_blocks.11.0.emb_layers.1.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.11.0.emb_layers.1.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.11.0.in_layers.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.11.0.in_layers.0.weight#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.11.0.in_layers.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.11.0.in_layers.2.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.input_blocks.11.0.out_layers.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.11.0.out_layers.0.weight#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.11.0.out_layers.3.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.11.0.out_layers.3.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.input_blocks.2.0.emb_layers.1.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.0.emb_layers.1.weight#torch.Size([320, 1280])#torch.float32
model.diffusion_model.input_blocks.2.0.in_layers.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.0.in_layers.0.weight#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.0.in_layers.2.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.0.in_layers.2.weight#torch.Size([320, 320, 3, 3])#torch.float32
model.diffusion_model.input_blocks.2.0.out_layers.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.0.out_layers.0.weight#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.0.out_layers.3.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.0.out_layers.3.weight#torch.Size([320, 320, 3, 3])#torch.float32
model.diffusion_model.input_blocks.2.1.norm.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.1.norm.weight#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.1.proj_in.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.1.proj_in.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.input_blocks.2.1.proj_out.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.1.proj_out.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn1.to_k.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn1.to_out.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn1.to_out.0.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn1.to_q.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn1.to_v.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_k.weight#torch.Size([320, 1024])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_out.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_out.0.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_q.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_v.weight#torch.Size([320, 1024])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.ff.net.0.proj.bias#torch.Size([2560])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.ff.net.0.proj.weight#torch.Size([2560, 320])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.ff.net.2.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.ff.net.2.weight#torch.Size([320, 1280])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.norm1.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.norm1.weight#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.norm2.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.norm2.weight#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.norm3.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.2.1.transformer_blocks.0.norm3.weight#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.3.0.op.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.3.0.op.weight#torch.Size([320, 320, 3, 3])#torch.float32
model.diffusion_model.input_blocks.4.0.emb_layers.1.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.4.0.emb_layers.1.weight#torch.Size([640, 1280])#torch.float32
model.diffusion_model.input_blocks.4.0.in_layers.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.4.0.in_layers.0.weight#torch.Size([320])#torch.float32
model.diffusion_model.input_blocks.4.0.in_layers.2.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.4.0.in_layers.2.weight#torch.Size([640, 320, 3, 3])#torch.float32
model.diffusion_model.input_blocks.4.0.out_layers.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.4.0.out_layers.0.weight#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.4.0.out_layers.3.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.4.0.out_layers.3.weight#torch.Size([640, 640, 3, 3])#torch.float32
model.diffusion_model.input_blocks.4.0.skip_connection.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.4.0.skip_connection.weight#torch.Size([640, 320, 1, 1])#torch.float32
model.diffusion_model.input_blocks.4.1.norm.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.4.1.norm.weight#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.4.1.proj_in.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.4.1.proj_in.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.input_blocks.4.1.proj_out.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.4.1.proj_out.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn1.to_k.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn1.to_out.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn1.to_out.0.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn1.to_q.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn1.to_v.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_k.weight#torch.Size([640, 1024])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_out.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_out.0.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_q.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_v.weight#torch.Size([640, 1024])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.ff.net.0.proj.bias#torch.Size([5120])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.ff.net.0.proj.weight#torch.Size([5120, 640])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.ff.net.2.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.ff.net.2.weight#torch.Size([640, 2560])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.norm1.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.norm1.weight#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.norm2.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.norm2.weight#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.norm3.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.4.1.transformer_blocks.0.norm3.weight#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.0.emb_layers.1.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.0.emb_layers.1.weight#torch.Size([640, 1280])#torch.float32
model.diffusion_model.input_blocks.5.0.in_layers.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.0.in_layers.0.weight#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.0.in_layers.2.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.0.in_layers.2.weight#torch.Size([640, 640, 3, 3])#torch.float32
model.diffusion_model.input_blocks.5.0.out_layers.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.0.out_layers.0.weight#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.0.out_layers.3.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.0.out_layers.3.weight#torch.Size([640, 640, 3, 3])#torch.float32
model.diffusion_model.input_blocks.5.1.norm.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.1.norm.weight#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.1.proj_in.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.1.proj_in.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.input_blocks.5.1.proj_out.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.1.proj_out.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn1.to_k.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn1.to_out.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn1.to_out.0.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn1.to_q.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn1.to_v.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_k.weight#torch.Size([640, 1024])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_out.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_out.0.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_q.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_v.weight#torch.Size([640, 1024])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.ff.net.0.proj.bias#torch.Size([5120])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.ff.net.0.proj.weight#torch.Size([5120, 640])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.ff.net.2.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.ff.net.2.weight#torch.Size([640, 2560])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.norm1.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.norm1.weight#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.norm2.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.norm2.weight#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.norm3.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.5.1.transformer_blocks.0.norm3.weight#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.6.0.op.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.6.0.op.weight#torch.Size([640, 640, 3, 3])#torch.float32
model.diffusion_model.input_blocks.7.0.emb_layers.1.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.7.0.emb_layers.1.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.7.0.in_layers.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.7.0.in_layers.0.weight#torch.Size([640])#torch.float32
model.diffusion_model.input_blocks.7.0.in_layers.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.7.0.in_layers.2.weight#torch.Size([1280, 640, 3, 3])#torch.float32
model.diffusion_model.input_blocks.7.0.out_layers.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.7.0.out_layers.0.weight#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.7.0.out_layers.3.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.7.0.out_layers.3.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.input_blocks.7.0.skip_connection.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.7.0.skip_connection.weight#torch.Size([1280, 640, 1, 1])#torch.float32
model.diffusion_model.input_blocks.7.1.norm.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.7.1.norm.weight#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.7.1.proj_in.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.7.1.proj_in.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.7.1.proj_out.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.7.1.proj_out.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn1.to_k.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn1.to_out.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn1.to_out.0.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn1.to_q.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn1.to_v.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_k.weight#torch.Size([1280, 1024])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_out.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_out.0.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_q.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_v.weight#torch.Size([1280, 1024])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.ff.net.0.proj.bias#torch.Size([10240])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.ff.net.0.proj.weight#torch.Size([10240, 1280])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.ff.net.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.ff.net.2.weight#torch.Size([1280, 5120])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.norm1.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.norm1.weight#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.norm2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.norm2.weight#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.norm3.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.7.1.transformer_blocks.0.norm3.weight#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.0.emb_layers.1.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.0.emb_layers.1.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.8.0.in_layers.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.0.in_layers.0.weight#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.0.in_layers.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.0.in_layers.2.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.input_blocks.8.0.out_layers.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.0.out_layers.0.weight#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.0.out_layers.3.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.0.out_layers.3.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.input_blocks.8.1.norm.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.1.norm.weight#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.1.proj_in.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.1.proj_in.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.8.1.proj_out.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.1.proj_out.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn1.to_k.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn1.to_out.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn1.to_out.0.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn1.to_q.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn1.to_v.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_k.weight#torch.Size([1280, 1024])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_out.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_out.0.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_q.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_v.weight#torch.Size([1280, 1024])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.ff.net.0.proj.bias#torch.Size([10240])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.ff.net.0.proj.weight#torch.Size([10240, 1280])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.ff.net.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.ff.net.2.weight#torch.Size([1280, 5120])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.norm1.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.norm1.weight#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.norm2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.norm2.weight#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.norm3.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.8.1.transformer_blocks.0.norm3.weight#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.9.0.op.bias#torch.Size([1280])#torch.float32
model.diffusion_model.input_blocks.9.0.op.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.middle_block.0.emb_layers.1.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.0.emb_layers.1.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.middle_block.0.in_layers.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.0.in_layers.0.weight#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.0.in_layers.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.0.in_layers.2.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.middle_block.0.out_layers.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.0.out_layers.0.weight#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.0.out_layers.3.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.0.out_layers.3.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.middle_block.1.norm.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.1.norm.weight#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.1.proj_in.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.1.proj_in.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.middle_block.1.proj_out.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.1.proj_out.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.attn1.to_k.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.attn1.to_out.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.attn1.to_out.0.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.attn1.to_q.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.attn1.to_v.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_k.weight#torch.Size([1280, 1024])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_out.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_out.0.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_q.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_v.weight#torch.Size([1280, 1024])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.ff.net.0.proj.bias#torch.Size([10240])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.ff.net.0.proj.weight#torch.Size([10240, 1280])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.ff.net.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.ff.net.2.weight#torch.Size([1280, 5120])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.norm1.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.norm1.weight#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.norm2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.norm2.weight#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.norm3.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.1.transformer_blocks.0.norm3.weight#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.2.emb_layers.1.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.2.emb_layers.1.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.middle_block.2.in_layers.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.2.in_layers.0.weight#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.2.in_layers.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.2.in_layers.2.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.middle_block.2.out_layers.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.2.out_layers.0.weight#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.2.out_layers.3.bias#torch.Size([1280])#torch.float32
model.diffusion_model.middle_block.2.out_layers.3.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.out.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.out.0.weight#torch.Size([320])#torch.float32
model.diffusion_model.out.2.bias#torch.Size([4])#torch.float32
model.diffusion_model.out.2.weight#torch.Size([4, 320, 3, 3])#torch.float32
model.diffusion_model.output_blocks.0.0.emb_layers.1.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.0.0.emb_layers.1.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.0.0.in_layers.0.bias#torch.Size([2560])#torch.float32
model.diffusion_model.output_blocks.0.0.in_layers.0.weight#torch.Size([2560])#torch.float32
model.diffusion_model.output_blocks.0.0.in_layers.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.0.0.in_layers.2.weight#torch.Size([1280, 2560, 3, 3])#torch.float32
model.diffusion_model.output_blocks.0.0.out_layers.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.0.0.out_layers.0.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.0.0.out_layers.3.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.0.0.out_layers.3.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.output_blocks.0.0.skip_connection.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.0.0.skip_connection.weight#torch.Size([1280, 2560, 1, 1])#torch.float32
model.diffusion_model.output_blocks.1.0.emb_layers.1.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.1.0.emb_layers.1.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.1.0.in_layers.0.bias#torch.Size([2560])#torch.float32
model.diffusion_model.output_blocks.1.0.in_layers.0.weight#torch.Size([2560])#torch.float32
model.diffusion_model.output_blocks.1.0.in_layers.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.1.0.in_layers.2.weight#torch.Size([1280, 2560, 3, 3])#torch.float32
model.diffusion_model.output_blocks.1.0.out_layers.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.1.0.out_layers.0.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.1.0.out_layers.3.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.1.0.out_layers.3.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.output_blocks.1.0.skip_connection.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.1.0.skip_connection.weight#torch.Size([1280, 2560, 1, 1])#torch.float32
model.diffusion_model.output_blocks.10.0.emb_layers.1.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.10.0.emb_layers.1.weight#torch.Size([320, 1280])#torch.float32
model.diffusion_model.output_blocks.10.0.in_layers.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.10.0.in_layers.0.weight#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.10.0.in_layers.2.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.10.0.in_layers.2.weight#torch.Size([320, 640, 3, 3])#torch.float32
model.diffusion_model.output_blocks.10.0.out_layers.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.10.0.out_layers.0.weight#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.10.0.out_layers.3.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.10.0.out_layers.3.weight#torch.Size([320, 320, 3, 3])#torch.float32
model.diffusion_model.output_blocks.10.0.skip_connection.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.10.0.skip_connection.weight#torch.Size([320, 640, 1, 1])#torch.float32
model.diffusion_model.output_blocks.10.1.norm.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.10.1.norm.weight#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.10.1.proj_in.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.10.1.proj_in.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.10.1.proj_out.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.10.1.proj_out.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn1.to_k.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn1.to_out.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn1.to_out.0.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn1.to_q.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn1.to_v.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn2.to_k.weight#torch.Size([320, 1024])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn2.to_out.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn2.to_out.0.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn2.to_q.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn2.to_v.weight#torch.Size([320, 1024])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.ff.net.0.proj.bias#torch.Size([2560])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.ff.net.0.proj.weight#torch.Size([2560, 320])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.ff.net.2.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.ff.net.2.weight#torch.Size([320, 1280])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.norm1.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.norm1.weight#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.norm2.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.norm2.weight#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.norm3.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.10.1.transformer_blocks.0.norm3.weight#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.0.emb_layers.1.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.0.emb_layers.1.weight#torch.Size([320, 1280])#torch.float32
model.diffusion_model.output_blocks.11.0.in_layers.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.11.0.in_layers.0.weight#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.11.0.in_layers.2.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.0.in_layers.2.weight#torch.Size([320, 640, 3, 3])#torch.float32
model.diffusion_model.output_blocks.11.0.out_layers.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.0.out_layers.0.weight#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.0.out_layers.3.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.0.out_layers.3.weight#torch.Size([320, 320, 3, 3])#torch.float32
model.diffusion_model.output_blocks.11.0.skip_connection.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.0.skip_connection.weight#torch.Size([320, 640, 1, 1])#torch.float32
model.diffusion_model.output_blocks.11.1.norm.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.1.norm.weight#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.1.proj_in.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.1.proj_in.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.11.1.proj_out.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.1.proj_out.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn1.to_k.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn1.to_out.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn1.to_out.0.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn1.to_q.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn1.to_v.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn2.to_k.weight#torch.Size([320, 1024])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn2.to_out.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn2.to_out.0.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn2.to_q.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn2.to_v.weight#torch.Size([320, 1024])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.ff.net.0.proj.bias#torch.Size([2560])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.ff.net.0.proj.weight#torch.Size([2560, 320])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.ff.net.2.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.ff.net.2.weight#torch.Size([320, 1280])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.norm1.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.norm1.weight#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.norm2.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.norm2.weight#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.norm3.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.11.1.transformer_blocks.0.norm3.weight#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.2.0.emb_layers.1.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.2.0.emb_layers.1.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.2.0.in_layers.0.bias#torch.Size([2560])#torch.float32
model.diffusion_model.output_blocks.2.0.in_layers.0.weight#torch.Size([2560])#torch.float32
model.diffusion_model.output_blocks.2.0.in_layers.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.2.0.in_layers.2.weight#torch.Size([1280, 2560, 3, 3])#torch.float32
model.diffusion_model.output_blocks.2.0.out_layers.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.2.0.out_layers.0.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.2.0.out_layers.3.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.2.0.out_layers.3.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.output_blocks.2.0.skip_connection.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.2.0.skip_connection.weight#torch.Size([1280, 2560, 1, 1])#torch.float32
model.diffusion_model.output_blocks.2.1.conv.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.2.1.conv.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.output_blocks.3.0.emb_layers.1.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.3.0.emb_layers.1.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.3.0.in_layers.0.bias#torch.Size([2560])#torch.float32
model.diffusion_model.output_blocks.3.0.in_layers.0.weight#torch.Size([2560])#torch.float32
model.diffusion_model.output_blocks.3.0.in_layers.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.3.0.in_layers.2.weight#torch.Size([1280, 2560, 3, 3])#torch.float32
model.diffusion_model.output_blocks.3.0.out_layers.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.3.0.out_layers.0.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.3.0.out_layers.3.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.3.0.out_layers.3.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.output_blocks.3.0.skip_connection.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.3.0.skip_connection.weight#torch.Size([1280, 2560, 1, 1])#torch.float32
model.diffusion_model.output_blocks.3.1.norm.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.3.1.norm.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.3.1.proj_in.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.3.1.proj_in.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.3.1.proj_out.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.3.1.proj_out.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_k.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_out.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_out.0.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_q.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_v.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_k.weight#torch.Size([1280, 1024])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_out.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_out.0.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_q.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_v.weight#torch.Size([1280, 1024])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.ff.net.0.proj.bias#torch.Size([10240])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.ff.net.0.proj.weight#torch.Size([10240, 1280])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.ff.net.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.ff.net.2.weight#torch.Size([1280, 5120])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.norm1.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.norm1.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.norm2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.norm2.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.norm3.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.3.1.transformer_blocks.0.norm3.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.0.emb_layers.1.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.0.emb_layers.1.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.4.0.in_layers.0.bias#torch.Size([2560])#torch.float32
model.diffusion_model.output_blocks.4.0.in_layers.0.weight#torch.Size([2560])#torch.float32
model.diffusion_model.output_blocks.4.0.in_layers.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.0.in_layers.2.weight#torch.Size([1280, 2560, 3, 3])#torch.float32
model.diffusion_model.output_blocks.4.0.out_layers.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.0.out_layers.0.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.0.out_layers.3.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.0.out_layers.3.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.output_blocks.4.0.skip_connection.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.0.skip_connection.weight#torch.Size([1280, 2560, 1, 1])#torch.float32
model.diffusion_model.output_blocks.4.1.norm.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.1.norm.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.1.proj_in.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.1.proj_in.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.4.1.proj_out.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.1.proj_out.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_k.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_out.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_out.0.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_q.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_v.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_k.weight#torch.Size([1280, 1024])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_out.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_out.0.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_q.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_v.weight#torch.Size([1280, 1024])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.ff.net.0.proj.bias#torch.Size([10240])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.ff.net.0.proj.weight#torch.Size([10240, 1280])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.ff.net.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.ff.net.2.weight#torch.Size([1280, 5120])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.norm1.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.norm1.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.norm2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.norm2.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.norm3.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.4.1.transformer_blocks.0.norm3.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.0.emb_layers.1.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.0.emb_layers.1.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.5.0.in_layers.0.bias#torch.Size([1920])#torch.float32
model.diffusion_model.output_blocks.5.0.in_layers.0.weight#torch.Size([1920])#torch.float32
model.diffusion_model.output_blocks.5.0.in_layers.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.0.in_layers.2.weight#torch.Size([1280, 1920, 3, 3])#torch.float32
model.diffusion_model.output_blocks.5.0.out_layers.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.0.out_layers.0.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.0.out_layers.3.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.0.out_layers.3.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.output_blocks.5.0.skip_connection.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.0.skip_connection.weight#torch.Size([1280, 1920, 1, 1])#torch.float32
model.diffusion_model.output_blocks.5.1.norm.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.1.norm.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.1.proj_in.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.1.proj_in.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.5.1.proj_out.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.1.proj_out.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_k.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_out.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_out.0.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_q.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_v.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_k.weight#torch.Size([1280, 1024])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_out.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_out.0.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_q.weight#torch.Size([1280, 1280])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_v.weight#torch.Size([1280, 1024])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.ff.net.0.proj.bias#torch.Size([10240])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.ff.net.0.proj.weight#torch.Size([10240, 1280])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.ff.net.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.ff.net.2.weight#torch.Size([1280, 5120])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.norm1.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.norm1.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.norm2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.norm2.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.norm3.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.1.transformer_blocks.0.norm3.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.2.conv.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.5.2.conv.weight#torch.Size([1280, 1280, 3, 3])#torch.float32
model.diffusion_model.output_blocks.6.0.emb_layers.1.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.6.0.emb_layers.1.weight#torch.Size([640, 1280])#torch.float32
model.diffusion_model.output_blocks.6.0.in_layers.0.bias#torch.Size([1920])#torch.float32
model.diffusion_model.output_blocks.6.0.in_layers.0.weight#torch.Size([1920])#torch.float32
model.diffusion_model.output_blocks.6.0.in_layers.2.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.6.0.in_layers.2.weight#torch.Size([640, 1920, 3, 3])#torch.float32
model.diffusion_model.output_blocks.6.0.out_layers.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.6.0.out_layers.0.weight#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.6.0.out_layers.3.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.6.0.out_layers.3.weight#torch.Size([640, 640, 3, 3])#torch.float32
model.diffusion_model.output_blocks.6.0.skip_connection.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.6.0.skip_connection.weight#torch.Size([640, 1920, 1, 1])#torch.float32
model.diffusion_model.output_blocks.6.1.norm.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.6.1.norm.weight#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.6.1.proj_in.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.6.1.proj_in.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.6.1.proj_out.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.6.1.proj_out.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn1.to_k.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn1.to_out.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn1.to_out.0.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn1.to_q.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn1.to_v.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn2.to_k.weight#torch.Size([640, 1024])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn2.to_out.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn2.to_out.0.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn2.to_q.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn2.to_v.weight#torch.Size([640, 1024])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.ff.net.0.proj.bias#torch.Size([5120])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.ff.net.0.proj.weight#torch.Size([5120, 640])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.ff.net.2.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.ff.net.2.weight#torch.Size([640, 2560])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.norm1.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.norm1.weight#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.norm2.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.norm2.weight#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.norm3.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.6.1.transformer_blocks.0.norm3.weight#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.0.emb_layers.1.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.0.emb_layers.1.weight#torch.Size([640, 1280])#torch.float32
model.diffusion_model.output_blocks.7.0.in_layers.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.7.0.in_layers.0.weight#torch.Size([1280])#torch.float32
model.diffusion_model.output_blocks.7.0.in_layers.2.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.0.in_layers.2.weight#torch.Size([640, 1280, 3, 3])#torch.float32
model.diffusion_model.output_blocks.7.0.out_layers.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.0.out_layers.0.weight#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.0.out_layers.3.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.0.out_layers.3.weight#torch.Size([640, 640, 3, 3])#torch.float32
model.diffusion_model.output_blocks.7.0.skip_connection.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.0.skip_connection.weight#torch.Size([640, 1280, 1, 1])#torch.float32
model.diffusion_model.output_blocks.7.1.norm.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.1.norm.weight#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.1.proj_in.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.1.proj_in.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.7.1.proj_out.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.1.proj_out.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn1.to_k.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn1.to_out.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn1.to_out.0.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn1.to_q.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn1.to_v.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn2.to_k.weight#torch.Size([640, 1024])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn2.to_out.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn2.to_out.0.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn2.to_q.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn2.to_v.weight#torch.Size([640, 1024])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.ff.net.0.proj.bias#torch.Size([5120])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.ff.net.0.proj.weight#torch.Size([5120, 640])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.ff.net.2.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.ff.net.2.weight#torch.Size([640, 2560])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.norm1.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.norm1.weight#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.norm2.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.norm2.weight#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.norm3.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.7.1.transformer_blocks.0.norm3.weight#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.0.emb_layers.1.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.0.emb_layers.1.weight#torch.Size([640, 1280])#torch.float32
model.diffusion_model.output_blocks.8.0.in_layers.0.bias#torch.Size([960])#torch.float32
model.diffusion_model.output_blocks.8.0.in_layers.0.weight#torch.Size([960])#torch.float32
model.diffusion_model.output_blocks.8.0.in_layers.2.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.0.in_layers.2.weight#torch.Size([640, 960, 3, 3])#torch.float32
model.diffusion_model.output_blocks.8.0.out_layers.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.0.out_layers.0.weight#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.0.out_layers.3.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.0.out_layers.3.weight#torch.Size([640, 640, 3, 3])#torch.float32
model.diffusion_model.output_blocks.8.0.skip_connection.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.0.skip_connection.weight#torch.Size([640, 960, 1, 1])#torch.float32
model.diffusion_model.output_blocks.8.1.norm.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.1.norm.weight#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.1.proj_in.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.1.proj_in.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.8.1.proj_out.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.1.proj_out.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn1.to_k.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn1.to_out.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn1.to_out.0.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn1.to_q.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn1.to_v.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn2.to_k.weight#torch.Size([640, 1024])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn2.to_out.0.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn2.to_out.0.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn2.to_q.weight#torch.Size([640, 640])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn2.to_v.weight#torch.Size([640, 1024])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.ff.net.0.proj.bias#torch.Size([5120])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.ff.net.0.proj.weight#torch.Size([5120, 640])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.ff.net.2.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.ff.net.2.weight#torch.Size([640, 2560])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.norm1.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.norm1.weight#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.norm2.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.norm2.weight#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.norm3.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.1.transformer_blocks.0.norm3.weight#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.2.conv.bias#torch.Size([640])#torch.float32
model.diffusion_model.output_blocks.8.2.conv.weight#torch.Size([640, 640, 3, 3])#torch.float32
model.diffusion_model.output_blocks.9.0.emb_layers.1.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.9.0.emb_layers.1.weight#torch.Size([320, 1280])#torch.float32
model.diffusion_model.output_blocks.9.0.in_layers.0.bias#torch.Size([960])#torch.float32
model.diffusion_model.output_blocks.9.0.in_layers.0.weight#torch.Size([960])#torch.float32
model.diffusion_model.output_blocks.9.0.in_layers.2.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.9.0.in_layers.2.weight#torch.Size([320, 960, 3, 3])#torch.float32
model.diffusion_model.output_blocks.9.0.out_layers.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.9.0.out_layers.0.weight#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.9.0.out_layers.3.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.9.0.out_layers.3.weight#torch.Size([320, 320, 3, 3])#torch.float32
model.diffusion_model.output_blocks.9.0.skip_connection.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.9.0.skip_connection.weight#torch.Size([320, 960, 1, 1])#torch.float32
model.diffusion_model.output_blocks.9.1.norm.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.9.1.norm.weight#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.9.1.proj_in.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.9.1.proj_in.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.9.1.proj_out.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.9.1.proj_out.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn1.to_k.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn1.to_out.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn1.to_out.0.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn1.to_q.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn1.to_v.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn2.to_k.weight#torch.Size([320, 1024])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn2.to_out.0.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn2.to_out.0.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn2.to_q.weight#torch.Size([320, 320])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn2.to_v.weight#torch.Size([320, 1024])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.ff.net.0.proj.bias#torch.Size([2560])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.ff.net.0.proj.weight#torch.Size([2560, 320])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.ff.net.2.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.ff.net.2.weight#torch.Size([320, 1280])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.norm1.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.norm1.weight#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.norm2.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.norm2.weight#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.norm3.bias#torch.Size([320])#torch.float32
model.diffusion_model.output_blocks.9.1.transformer_blocks.0.norm3.weight#torch.Size([320])#torch.float32
model.diffusion_model.time_embed.0.bias#torch.Size([1280])#torch.float32
model.diffusion_model.time_embed.0.weight#torch.Size([1280, 320])#torch.float32
model.diffusion_model.time_embed.2.bias#torch.Size([1280])#torch.float32
model.diffusion_model.time_embed.2.weight#torch.Size([1280, 1280])#torch.float32
