cond_stage_model.transformer.text_model.embeddings.position_embedding.weight#torch.Size([77, 768])#torch.float32
cond_stage_model.transformer.text_model.embeddings.token_embedding.weight#torch.Size([49408, 768])#torch.float32
cond_stage_model.transformer.text_model.final_layer_norm.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.final_layer_norm.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.0.mlp.fc1.bias#torch.Size([3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.0.mlp.fc1.weight#torch.Size([3072, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.0.mlp.fc2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.0.mlp.fc2.weight#torch.Size([768, 3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.0.layer_norm1.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.0.layer_norm1.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.0.layer_norm2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.0.layer_norm2.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.k_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.k_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.q_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.q_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.v_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.v_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.out_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.out_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.1.mlp.fc1.bias#torch.Size([3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.1.mlp.fc1.weight#torch.Size([3072, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.1.mlp.fc2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.1.mlp.fc2.weight#torch.Size([768, 3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.1.layer_norm1.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.1.layer_norm1.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.1.layer_norm2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.1.layer_norm2.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.k_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.k_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.q_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.q_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.v_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.v_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.out_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.out_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.10.mlp.fc1.bias#torch.Size([3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.10.mlp.fc1.weight#torch.Size([3072, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.10.mlp.fc2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.10.mlp.fc2.weight#torch.Size([768, 3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.10.layer_norm1.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.10.layer_norm1.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.10.layer_norm2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.10.layer_norm2.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.k_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.k_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.q_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.q_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.v_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.v_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.out_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.out_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.11.mlp.fc1.bias#torch.Size([3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.11.mlp.fc1.weight#torch.Size([3072, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.11.mlp.fc2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.11.mlp.fc2.weight#torch.Size([768, 3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.11.layer_norm1.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.11.layer_norm1.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.11.layer_norm2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.11.layer_norm2.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.k_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.k_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.q_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.q_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.v_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.v_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.out_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.out_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.2.mlp.fc1.bias#torch.Size([3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.2.mlp.fc1.weight#torch.Size([3072, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.2.mlp.fc2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.2.mlp.fc2.weight#torch.Size([768, 3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.2.layer_norm1.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.2.layer_norm1.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.2.layer_norm2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.2.layer_norm2.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.k_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.k_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.q_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.q_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.v_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.v_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.out_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.out_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.3.mlp.fc1.bias#torch.Size([3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.3.mlp.fc1.weight#torch.Size([3072, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.3.mlp.fc2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.3.mlp.fc2.weight#torch.Size([768, 3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.3.layer_norm1.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.3.layer_norm1.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.3.layer_norm2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.3.layer_norm2.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.k_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.k_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.q_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.q_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.v_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.v_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.out_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.out_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.4.mlp.fc1.bias#torch.Size([3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.4.mlp.fc1.weight#torch.Size([3072, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.4.mlp.fc2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.4.mlp.fc2.weight#torch.Size([768, 3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.4.layer_norm1.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.4.layer_norm1.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.4.layer_norm2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.4.layer_norm2.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.k_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.k_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.q_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.q_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.v_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.v_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.out_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.out_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.5.mlp.fc1.bias#torch.Size([3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.5.mlp.fc1.weight#torch.Size([3072, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.5.mlp.fc2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.5.mlp.fc2.weight#torch.Size([768, 3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.5.layer_norm1.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.5.layer_norm1.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.5.layer_norm2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.5.layer_norm2.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.k_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.k_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.q_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.q_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.v_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.v_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.out_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.out_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.6.mlp.fc1.bias#torch.Size([3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.6.mlp.fc1.weight#torch.Size([3072, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.6.mlp.fc2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.6.mlp.fc2.weight#torch.Size([768, 3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.6.layer_norm1.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.6.layer_norm1.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.6.layer_norm2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.6.layer_norm2.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.k_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.k_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.q_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.q_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.v_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.v_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.out_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.out_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.7.mlp.fc1.bias#torch.Size([3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.7.mlp.fc1.weight#torch.Size([3072, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.7.mlp.fc2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.7.mlp.fc2.weight#torch.Size([768, 3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.7.layer_norm1.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.7.layer_norm1.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.7.layer_norm2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.7.layer_norm2.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.k_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.k_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.q_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.q_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.v_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.v_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.out_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.out_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.8.mlp.fc1.bias#torch.Size([3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.8.mlp.fc1.weight#torch.Size([3072, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.8.mlp.fc2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.8.mlp.fc2.weight#torch.Size([768, 3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.8.layer_norm1.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.8.layer_norm1.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.8.layer_norm2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.8.layer_norm2.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.k_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.k_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.q_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.q_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.v_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.v_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.out_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.out_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.9.mlp.fc1.bias#torch.Size([3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.9.mlp.fc1.weight#torch.Size([3072, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.9.mlp.fc2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.9.mlp.fc2.weight#torch.Size([768, 3072])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.9.layer_norm1.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.9.layer_norm1.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.9.layer_norm2.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.9.layer_norm2.weight#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.k_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.k_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.q_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.q_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.v_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.v_proj.weight#torch.Size([768, 768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.out_proj.bias#torch.Size([768])#torch.float32
cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.out_proj.weight#torch.Size([768, 768])#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, 1, 1])#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, 1, 1])#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, 768])#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, 768])#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, 1, 1])#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, 1, 1])#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, 768])#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, 768])#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, 1, 1])#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, 1, 1])#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, 768])#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, 768])#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, 1, 1])#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, 1, 1])#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, 768])#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, 768])#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, 1, 1])#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, 1, 1])#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, 768])#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, 768])#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, 1, 1])#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, 1, 1])#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, 768])#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, 768])#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, 1, 1])#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, 1, 1])#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, 768])#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, 768])#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, 1, 1])#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, 1, 1])#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, 768])#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, 768])#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, 1, 1])#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, 1, 1])#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, 768])#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, 768])#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, 1, 1])#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, 1, 1])#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, 768])#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, 768])#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, 1, 1])#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, 1, 1])#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, 768])#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, 768])#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, 1, 1])#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, 1, 1])#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, 768])#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, 768])#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, 1, 1])#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, 1, 1])#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, 768])#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, 768])#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, 1, 1])#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, 1, 1])#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, 768])#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, 768])#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, 1, 1])#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, 1, 1])#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, 768])#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, 768])#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, 1, 1])#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, 1, 1])#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, 768])#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, 768])#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
