Skip to content
New issue

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

Sign up for GitHub

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

Already on GitHub? Sign in to your account

Jump to bottom

Qwen2.5-7b 剪枝推理报错 #441

Open
zeze813 opened this issue Nov 28, 2024 · 1 comment
Open

Qwen2.5-7b 剪枝推理报错 #441

zeze813 opened this issue Nov 28, 2024 · 1 comment

Comments

@zeze813
Copy link

zeze813 commented Nov 28, 2024

Some weights of Qwen2ForCausalLM were not initialized from the model checkpoint at ./output and are newly initialized because the shapes did not match:

  • model.layers.0.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.0.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.0.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.0.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.0.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.0.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.0.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.1.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.1.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.1.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.1.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.1.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.1.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.1.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.10.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.10.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.10.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.10.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.10.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.10.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.10.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.11.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.11.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.11.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.11.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.11.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.11.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.11.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.12.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.12.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.12.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.12.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.12.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.12.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.12.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.13.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.13.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.13.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.13.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.13.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.13.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.13.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.14.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.14.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.14.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.14.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.14.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.14.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.14.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.15.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.15.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.15.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.15.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.15.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.15.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.15.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.16.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.16.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.16.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.16.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.16.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.16.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.16.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.17.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.17.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.17.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.17.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.17.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.17.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.17.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.18.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.18.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.18.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.18.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.18.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.18.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.18.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.19.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.19.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.19.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.19.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.19.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.19.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.19.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.2.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.2.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.2.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.2.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.2.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.2.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.2.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.20.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.20.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.20.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.20.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.20.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.20.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.20.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.21.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.21.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.21.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.21.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.21.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.21.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.21.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.22.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.22.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.22.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.22.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.22.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.22.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.22.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.23.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.23.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.23.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.23.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.23.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.23.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.23.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.24.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.24.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.24.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.24.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.24.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.24.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.24.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.25.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.25.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.25.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.25.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.25.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.25.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.25.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.26.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.26.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.26.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.26.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.26.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.26.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.26.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.27.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.27.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.27.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.27.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.27.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.27.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.27.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.3.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.3.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.3.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.3.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.3.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.3.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.3.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.4.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.4.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.4.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.4.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.4.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.4.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.4.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.5.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.5.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.5.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.5.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.5.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.5.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.5.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.6.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.6.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.6.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.6.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.6.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.6.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.6.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.7.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.7.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.7.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.7.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.7.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.7.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.7.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.8.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.8.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.8.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.8.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.8.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.8.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.8.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.9.self_attn.k_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.9.self_attn.k_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) in the model instantiated
  • model.layers.9.self_attn.o_proj.weight: found shape torch.Size([1792, 2048]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.9.self_attn.q_proj.bias: found shape torch.Size([2048]) in the checkpoint and torch.Size([1792]) in the model instantiated
  • model.layers.9.self_attn.q_proj.weight: found shape torch.Size([2048, 1792]) in the checkpoint and torch.Size([1792, 1792]) in the model instantiated
  • model.layers.9.self_attn.v_proj.bias: found shape torch.Size([512]) in the checkpoint and torch.Size([448]) in the model instantiated
  • model.layers.9.self_attn.v_proj.weight: found shape torch.Size([512, 1792]) in the checkpoint and torch.Size([448, 1792]) 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.
    Traceback (most recent call last):
    File "/home/llm_infer.py", line 84, in
    infer_qwen(model_name='./output', messages=messages,
    File "/home/llm_infer.py", line 7, in infer_qwen
    model = AutoModelForCausalLM.from_pretrained(
    File "/usr/local/lib/python3.10/dist-packages/transformers/models/auto/auto_factory.py", line 564, in from_pretrained
    return model_class.from_pretrained(
    File "/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py", line 4303, in from_pretrained
    dispatch_model(model, **device_map_kwargs)
    File "/usr/local/lib/python3.10/dist-packages/accelerate/big_modeling.py", line 494, in dispatch_model
    model.to(device)
    File "/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py", line 3157, in to
    return super().to(*args, **kwargs)
    File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1174, in to
    return self._apply(convert)
    File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 780, in _apply
    module._apply(fn)
    File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 780, in _apply
    module._apply(fn)
    File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 780, in _apply
    module._apply(fn)
    [Previous line repeated 2 more times]
    File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 805, in _apply
    param_applied = fn(param)
    File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1167, in convert
    raise NotImplementedError(
    NotImplementedError: Cannot copy out of meta tensor; no data! Please use torch.nn.Module.to_empty() instead of torch.nn.Module.to() when moving module from meta to a different device.
@zeze813
Copy link
Author

zeze813 commented Nov 29, 2024

已解决,报错模型时,用torch.save,加载模型torch.load,tokenizer那些照旧就行

VainF added a commit that referenced this issue Nov 30, 2024
@VainF
[#441,#439,#436]Fixed a Save & Load issue for Qwen2
85aa041
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@zeze813