Train dse model saved model when loading contain mismatched dimensions

Hi below is my error script
Specifically, I have used example/dse/qwen/train to train the model and it has been saved locally; then when I try to load it; i always get size mismatch (note here I already put ignore_mismatched_sizes=True)
Just want to know Does this impact the model effectiveness when used?

```
-ft_2 and are newly initialized because the shapes did not match:
- lm_head.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([151936, 1536]) in the model instantiated
- model.language_model.embed_tokens.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([151936, 1536]) in the model instantiated
- model.language_model.layers.0.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.0.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.0.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.0.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.0.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.0.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.0.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.1.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.1.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.1.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.1.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.1.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.1.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.1.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.10.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.10.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.10.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.10.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.10.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.10.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.10.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.11.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.11.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.11.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.11.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.11.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.11.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.11.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.12.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.12.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.12.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.12.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.12.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.12.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.12.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.13.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.13.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.13.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.13.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.13.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.13.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.13.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.14.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.14.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.14.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.14.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.14.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.14.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.14.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.15.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.15.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.15.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.15.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.15.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.15.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.15.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.16.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.16.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.16.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.16.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.16.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.16.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.16.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.17.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.17.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.17.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.17.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.17.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.17.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.17.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.18.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.18.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.18.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.18.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.18.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.18.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.18.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.19.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.19.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.19.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.19.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.19.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.19.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.19.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.2.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.2.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.2.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.2.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.2.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.2.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.2.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.20.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.20.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.20.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.20.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.20.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.20.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.20.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.21.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.21.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.21.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.21.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.21.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.21.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.21.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.22.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.22.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.22.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.22.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.22.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.22.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.22.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.23.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.23.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.23.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.23.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.23.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.23.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.23.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.24.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.24.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.24.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.24.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.24.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.24.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.24.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.25.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.25.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.25.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.25.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.25.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.25.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.25.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.26.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.26.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.26.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.26.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.26.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.26.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.26.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.27.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.27.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.27.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.27.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.27.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.27.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.27.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.3.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.3.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.3.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.3.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.3.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.3.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.3.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.4.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.4.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.4.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.4.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.4.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.4.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.4.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.5.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.5.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.5.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.5.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.5.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.5.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.5.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.6.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.6.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.6.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.6.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.6.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.6.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.6.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.7.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.7.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.7.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.7.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.7.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.7.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.7.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.8.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.8.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.8.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.8.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.8.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.8.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.8.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.9.mlp.down_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 8960]) in the model instantiated
- model.language_model.layers.9.mlp.gate_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.9.mlp.up_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([8960, 1536]) in the model instantiated
- model.language_model.layers.9.self_attn.k_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.language_model.layers.9.self_attn.o_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.9.self_attn.q_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 1536]) in the model instantiated
- model.language_model.layers.9.self_attn.v_proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([256, 1536]) in the model instantiated
- model.visual.blocks.0.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.0.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.0.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.0.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.1.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.1.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.1.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.1.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.10.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.10.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.10.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.10.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.11.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.11.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.11.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.11.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.12.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.12.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.12.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.12.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.13.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.13.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.13.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.13.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.14.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.14.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.14.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.14.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.15.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.15.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.15.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.15.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.16.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.16.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.16.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.16.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.17.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.17.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.17.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.17.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.18.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.18.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.18.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.18.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.19.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.19.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.19.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.19.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.2.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.2.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.2.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.2.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.20.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.20.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.20.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.20.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.21.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.21.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.21.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.21.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.22.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.22.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.22.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.22.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.23.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.23.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.23.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.23.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.24.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.24.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.24.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.24.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.25.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.25.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.25.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.25.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.26.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.26.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.26.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.26.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.27.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.27.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.27.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.27.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.28.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.28.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.28.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.28.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.29.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.29.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.29.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.29.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.3.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.3.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.3.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.3.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.30.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.30.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.30.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.30.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.31.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.31.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.31.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.31.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.4.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.4.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.4.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.4.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.5.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.5.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.5.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.5.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.6.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.6.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.6.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.6.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.7.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.7.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.7.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.7.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.8.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.8.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.8.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.8.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.blocks.9.attn.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 1280]) in the model instantiated
- model.visual.blocks.9.attn.qkv.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([3840, 1280]) in the model instantiated
- model.visual.blocks.9.mlp.fc1.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 1280]) in the model instantiated
- model.visual.blocks.9.mlp.fc2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 5120]) in the model instantiated
- model.visual.merger.mlp.0.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([5120, 5120]) in the model instantiated
- model.visual.merger.mlp.2.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1536, 5120]) in the model instantiated
- model.visual.patch_embed.proj.weight: found shape torch.Size([0]) in the checkpoint and torch.Size([1280, 3, 2, 14, 14]) in the model instantiated
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
```



Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Train dse model saved model when loading contain mismatched dimensions #203

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Train dse model saved model when loading contain mismatched dimensions #203

Description

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions