raise RuntimeError(f"Error(s) in loading state_dict for {model.__class__.__name__}:\n\t{error_msg}") RuntimeError: Error(s) in loading state_dict for CLIPTextModel:

[zzingok]

raise RuntimeError(f"Error(s) in loading state_dict for {model.class.name}:\n\t{error_msg}") RuntimeError: Error(s) in loading state_dict for CLIPTextModel: size mismatch for text_model.embeddings.token_embedding.weight: copying a param with shape torch.Size([49408, 768]) from checkpoint, the shape in current model is torch.Size([49408, 512]). size mismatch for text_model.embeddings.position_embedding.weight: copying a param with shape torch.Size([77, 768]) from checkpoint, the shape in current model is torch.Size([77, 512]). size mismatch for text_model.encoder.layers.0.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.0.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.0.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.0.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.0.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.0.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.0.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.0.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.1.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.1.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.1.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.1.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.1.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.1.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.1.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.2.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.2.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.2.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.2.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.2.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.2.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.2.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.3.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.3.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.3.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.3.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.3.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.3.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.3.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.4.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.4.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.4.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.4.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.4.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.4.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.4.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.5.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.5.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.5.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.5.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.5.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.5.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.5.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.6.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.6.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.6.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.6.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.6.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.6.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.6.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.7.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.7.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.7.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.7.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.7.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.7.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.7.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.8.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.8.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.8.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.8.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.8.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.8.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.8.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.9.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.9.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.9.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.9.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.9.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.9.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.9.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.10.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.10.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.10.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.10.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.10.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.10.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.10.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.11.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.11.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.11.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.11.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.11.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.11.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.11.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.final_layer_norm.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.final_layer_norm.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]).

[SamStark-AW]

I think this is related to the different size of Stable diffusion version 1.4-5 and 2.0-1, maybe u have to check the version?

[CrossLee1]

@zzingok do you solve this problem?

[dedoogong]

I got the same problem when running both tool_add_control.py and tutorial_train.py. The used model is "v1-5-pruned.ckpt' from https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main. I think it is SD 1.5. Of course I used cldm_v15 for SD 1.5. Where is the parameter related to this attention size? I think ddconfig would be the one. but is it ok to change from 4 to 6 ? ddconfig: ch: 128 ch_mult: - 1 - 2 - 4 - 4

[dedoogong]

Plus, this error is related to CLIP model, not SD model as far as I guess. And there are a lot of other errors related to this bug. So I hope @lllyasviel make it clear.

[CreamyLong]

Fixed by install transformers==4.19.2.

[WenkunHe]

Fixed by install transformers==4.19.2.

Still not solved.

[WenkunHe]

Fixed by install transformers==4.19.2.

Still not solved.

Maybe I didn't download the correct weight. Is the v1-5-pruned.ckpt in this link OK? https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main

[WenkunHe]

raise RuntimeError(f"Error(s) in loading state_dict for {model.class.name}:\n\t{error_msg}") RuntimeError: Error(s) in loading state_dict for CLIPTextModel: size mismatch for text_model.embeddings.token_embedding.weight: copying a param with shape torch.Size([49408, 768]) from checkpoint, the shape in current model is torch.Size([49408, 512]). size mismatch for text_model.embeddings.position_embedding.weight: copying a param with shape torch.Size([77, 768]) from checkpoint, the shape in current model is torch.Size([77, 512]). size mismatch for text_model.encoder.layers.0.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.0.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.0.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.0.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.0.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.0.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.0.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.0.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.1.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.1.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.1.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.1.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.1.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.1.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.1.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.2.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.2.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.2.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.2.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.2.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.2.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.2.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.3.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.3.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.3.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.3.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.3.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.3.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.3.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.4.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.4.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.4.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.4.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.4.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.4.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.4.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.5.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.5.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.5.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.5.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.5.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.5.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.5.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.6.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.6.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.6.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.6.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.6.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.6.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.6.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.7.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.7.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.7.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.7.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.7.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.7.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.7.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.8.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.8.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.8.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.8.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.8.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.8.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.8.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.9.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.9.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.9.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.9.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.9.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.9.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.9.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.10.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.10.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.10.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.10.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.10.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.10.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.10.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.11.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.11.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.11.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.11.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.11.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.11.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.11.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.final_layer_norm.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.final_layer_norm.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]).

Have you solved this problem yet?

[comodo-bean]

raise RuntimeError(f"Error(s) in loading state_dict for {model.class.name}:\n\t{error_msg}") RuntimeError: Error(s) in loading state_dict for CLIPTextModel: size mismatch for text_model.embeddings.token_embedding.weight: copying a param with shape torch.Size([49408, 768]) from checkpoint, the shape in current model is torch.Size([49408, 512]). size mismatch for text_model.embeddings.position_embedding.weight: copying a param with shape torch.Size([77, 768]) from checkpoint, the shape in current model is torch.Size([77, 512]). size mismatch for text_model.encoder.layers.0.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.0.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.0.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.0.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.0.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.0.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.0.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.0.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.0.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.1.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.1.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.1.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.1.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.1.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.1.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.1.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.1.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.2.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.2.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.2.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.2.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.2.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.2.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.2.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.2.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.3.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.3.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.3.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.3.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.3.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.3.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.3.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.3.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.4.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.4.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.4.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.4.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.4.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.4.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.4.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.4.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.5.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.5.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.5.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.5.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.5.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.5.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.5.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.5.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.6.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.6.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.6.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.6.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.6.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.6.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.6.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.6.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.7.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.7.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.7.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.7.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.7.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.7.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.7.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.7.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.8.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.8.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.8.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.8.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.8.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.8.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.8.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.8.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.9.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.9.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.9.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.9.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.9.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.9.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.9.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.9.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.10.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.10.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.10.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.10.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.10.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.10.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.10.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.10.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.self_attn.k_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.11.self_attn.k_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.self_attn.v_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.11.self_attn.v_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.self_attn.q_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.11.self_attn.q_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.self_attn.out_proj.weight: copying a param with shape torch.Size([768, 768]) from checkpoint, the shape in current model is torch.Size([512, 512]). size mismatch for text_model.encoder.layers.11.self_attn.out_proj.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.layer_norm1.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.layer_norm1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.mlp.fc1.weight: copying a param with shape torch.Size([3072, 768]) from checkpoint, the shape in current model is torch.Size([2048, 512]). size mismatch for text_model.encoder.layers.11.mlp.fc1.bias: copying a param with shape torch.Size([3072]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for text_model.encoder.layers.11.mlp.fc2.weight: copying a param with shape torch.Size([768, 3072]) from checkpoint, the shape in current model is torch.Size([512, 2048]). size mismatch for text_model.encoder.layers.11.mlp.fc2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.layer_norm2.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.encoder.layers.11.layer_norm2.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.final_layer_norm.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for text_model.final_layer_norm.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([512]).

Have you solved this problem yet?

did you solved this problem yet?