API tools faq
paste
Advertisement
remghoost

alpaca model error

remghoost
Mar 22nd, 2023
154
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 59.68 KB | None | 0 0
raw download clone embed print report
  1. Loading alpaca-native-4bit...
  2. Loading model ...
  3. Traceback (most recent call last):
  4. File "/mnt/c/stable-diffusion/text-generation-webui/server.py", line 241, in <module>
  5. shared.model, shared.tokenizer = load_model(shared.model_name)
  6. File "/mnt/c/stable-diffusion/text-generation-webui/modules/models.py", line 101, in load_model
  7. model = load_quantized(model_name)
  8. File "/mnt/c/stable-diffusion/text-generation-webui/modules/GPTQ_loader.py", line 64, in load_quantized
  9. model = load_quant(str(path_to_model), str(pt_path), shared.args.gptq_bits)
  10. File "/mnt/c/stable-diffusion/text-generation-webui/repositories/GPTQ-for-LLaMa/llama.py", line 245, in load_quant
  11. model.load_state_dict(torch.load(checkpoint))
  12. File "/home/rem/miniconda3/envs/textgen/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2041, in load_state_dict
  13. raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
  14. RuntimeError: Error(s) in loading state_dict for LlamaForCausalLM:
  15. Missing key(s) in state_dict: "model.layers.0.self_attn.q_proj.zeros", "model.layers.0.self_attn.k_proj.zeros", "model.layers.0.self_attn.v_proj.zeros", "model.layers.0.self_attn.o_proj.zeros", "model.layers.0.mlp.gate_proj.zeros", "model.layers.0.mlp.down_proj.zeros", "model.layers.0.mlp.up_proj.zeros", "model.layers.1.self_attn.q_proj.zeros", "model.layers.1.self_attn.k_proj.zeros", "model.layers.1.self_attn.v_proj.zeros", "model.layers.1.self_attn.o_proj.zeros", "model.layers.1.mlp.gate_proj.zeros", "model.layers.1.mlp.down_proj.zeros", "model.layers.1.mlp.up_proj.zeros", "model.layers.2.self_attn.q_proj.zeros", "model.layers.2.self_attn.k_proj.zeros", "model.layers.2.self_attn.v_proj.zeros", "model.layers.2.self_attn.o_proj.zeros", "model.layers.2.mlp.gate_proj.zeros", "model.layers.2.mlp.down_proj.zeros", "model.layers.2.mlp.up_proj.zeros", "model.layers.3.self_attn.q_proj.zeros", "model.layers.3.self_attn.k_proj.zeros", "model.layers.3.self_attn.v_proj.zeros", "model.layers.3.self_attn.o_proj.zeros", "model.layers.3.mlp.gate_proj.zeros", "model.layers.3.mlp.down_proj.zeros", "model.layers.3.mlp.up_proj.zeros", "model.layers.4.self_attn.q_proj.zeros", "model.layers.4.self_attn.k_proj.zeros", "model.layers.4.self_attn.v_proj.zeros", "model.layers.4.self_attn.o_proj.zeros", "model.layers.4.mlp.gate_proj.zeros", "model.layers.4.mlp.down_proj.zeros", "model.layers.4.mlp.up_proj.zeros", "model.layers.5.self_attn.q_proj.zeros", "model.layers.5.self_attn.k_proj.zeros", "model.layers.5.self_attn.v_proj.zeros", "model.layers.5.self_attn.o_proj.zeros", "model.layers.5.mlp.gate_proj.zeros", "model.layers.5.mlp.down_proj.zeros", "model.layers.5.mlp.up_proj.zeros", "model.layers.6.self_attn.q_proj.zeros", "model.layers.6.self_attn.k_proj.zeros", "model.layers.6.self_attn.v_proj.zeros", "model.layers.6.self_attn.o_proj.zeros", "model.layers.6.mlp.gate_proj.zeros", "model.layers.6.mlp.down_proj.zeros", "model.layers.6.mlp.up_proj.zeros", "model.layers.7.self_attn.q_proj.zeros", "model.layers.7.self_attn.k_proj.zeros", "model.layers.7.self_attn.v_proj.zeros", "model.layers.7.self_attn.o_proj.zeros", "model.layers.7.mlp.gate_proj.zeros", "model.layers.7.mlp.down_proj.zeros", "model.layers.7.mlp.up_proj.zeros", "model.layers.8.self_attn.q_proj.zeros", "model.layers.8.self_attn.k_proj.zeros", "model.layers.8.self_attn.v_proj.zeros", "model.layers.8.self_attn.o_proj.zeros", "model.layers.8.mlp.gate_proj.zeros", "model.layers.8.mlp.down_proj.zeros", "model.layers.8.mlp.up_proj.zeros", "model.layers.9.self_attn.q_proj.zeros", "model.layers.9.self_attn.k_proj.zeros", "model.layers.9.self_attn.v_proj.zeros", "model.layers.9.self_attn.o_proj.zeros", "model.layers.9.mlp.gate_proj.zeros", "model.layers.9.mlp.down_proj.zeros", "model.layers.9.mlp.up_proj.zeros", "model.layers.10.self_attn.q_proj.zeros", "model.layers.10.self_attn.k_proj.zeros", "model.layers.10.self_attn.v_proj.zeros", "model.layers.10.self_attn.o_proj.zeros", "model.layers.10.mlp.gate_proj.zeros", "model.layers.10.mlp.down_proj.zeros", "model.layers.10.mlp.up_proj.zeros", "model.layers.11.self_attn.q_proj.zeros", "model.layers.11.self_attn.k_proj.zeros", "model.layers.11.self_attn.v_proj.zeros", "model.layers.11.self_attn.o_proj.zeros", "model.layers.11.mlp.gate_proj.zeros", "model.layers.11.mlp.down_proj.zeros", "model.layers.11.mlp.up_proj.zeros", "model.layers.12.self_attn.q_proj.zeros", "model.layers.12.self_attn.k_proj.zeros", "model.layers.12.self_attn.v_proj.zeros", "model.layers.12.self_attn.o_proj.zeros", "model.layers.12.mlp.gate_proj.zeros", "model.layers.12.mlp.down_proj.zeros", "model.layers.12.mlp.up_proj.zeros", "model.layers.13.self_attn.q_proj.zeros", "model.layers.13.self_attn.k_proj.zeros", "model.layers.13.self_attn.v_proj.zeros", "model.layers.13.self_attn.o_proj.zeros", "model.layers.13.mlp.gate_proj.zeros", "model.layers.13.mlp.down_proj.zeros", "model.layers.13.mlp.up_proj.zeros", "model.layers.14.self_attn.q_proj.zeros", "model.layers.14.self_attn.k_proj.zeros", "model.layers.14.self_attn.v_proj.zeros", "model.layers.14.self_attn.o_proj.zeros", "model.layers.14.mlp.gate_proj.zeros", "model.layers.14.mlp.down_proj.zeros", "model.layers.14.mlp.up_proj.zeros", "model.layers.15.self_attn.q_proj.zeros", "model.layers.15.self_attn.k_proj.zeros", "model.layers.15.self_attn.v_proj.zeros", "model.layers.15.self_attn.o_proj.zeros", "model.layers.15.mlp.gate_proj.zeros", "model.layers.15.mlp.down_proj.zeros", "model.layers.15.mlp.up_proj.zeros", "model.layers.16.self_attn.q_proj.zeros", "model.layers.16.self_attn.k_proj.zeros", "model.layers.16.self_attn.v_proj.zeros", "model.layers.16.self_attn.o_proj.zeros", "model.layers.16.mlp.gate_proj.zeros", "model.layers.16.mlp.down_proj.zeros", "model.layers.16.mlp.up_proj.zeros", "model.layers.17.self_attn.q_proj.zeros", "model.layers.17.self_attn.k_proj.zeros", "model.layers.17.self_attn.v_proj.zeros", "model.layers.17.self_attn.o_proj.zeros", "model.layers.17.mlp.gate_proj.zeros", "model.layers.17.mlp.down_proj.zeros", "model.layers.17.mlp.up_proj.zeros", "model.layers.18.self_attn.q_proj.zeros", "model.layers.18.self_attn.k_proj.zeros", "model.layers.18.self_attn.v_proj.zeros", "model.layers.18.self_attn.o_proj.zeros", "model.layers.18.mlp.gate_proj.zeros", "model.layers.18.mlp.down_proj.zeros", "model.layers.18.mlp.up_proj.zeros", "model.layers.19.self_attn.q_proj.zeros", "model.layers.19.self_attn.k_proj.zeros", "model.layers.19.self_attn.v_proj.zeros", "model.layers.19.self_attn.o_proj.zeros", "model.layers.19.mlp.gate_proj.zeros", "model.layers.19.mlp.down_proj.zeros", "model.layers.19.mlp.up_proj.zeros", "model.layers.20.self_attn.q_proj.zeros", "model.layers.20.self_attn.k_proj.zeros", "model.layers.20.self_attn.v_proj.zeros", "model.layers.20.self_attn.o_proj.zeros", "model.layers.20.mlp.gate_proj.zeros", "model.layers.20.mlp.down_proj.zeros", "model.layers.20.mlp.up_proj.zeros", "model.layers.21.self_attn.q_proj.zeros", "model.layers.21.self_attn.k_proj.zeros", "model.layers.21.self_attn.v_proj.zeros", "model.layers.21.self_attn.o_proj.zeros", "model.layers.21.mlp.gate_proj.zeros", "model.layers.21.mlp.down_proj.zeros", "model.layers.21.mlp.up_proj.zeros", "model.layers.22.self_attn.q_proj.zeros", "model.layers.22.self_attn.k_proj.zeros", "model.layers.22.self_attn.v_proj.zeros", "model.layers.22.self_attn.o_proj.zeros", "model.layers.22.mlp.gate_proj.zeros", "model.layers.22.mlp.down_proj.zeros", "model.layers.22.mlp.up_proj.zeros", "model.layers.23.self_attn.q_proj.zeros", "model.layers.23.self_attn.k_proj.zeros", "model.layers.23.self_attn.v_proj.zeros", "model.layers.23.self_attn.o_proj.zeros", "model.layers.23.mlp.gate_proj.zeros", "model.layers.23.mlp.down_proj.zeros", "model.layers.23.mlp.up_proj.zeros", "model.layers.24.self_attn.q_proj.zeros", "model.layers.24.self_attn.k_proj.zeros", "model.layers.24.self_attn.v_proj.zeros", "model.layers.24.self_attn.o_proj.zeros", "model.layers.24.mlp.gate_proj.zeros", "model.layers.24.mlp.down_proj.zeros", "model.layers.24.mlp.up_proj.zeros", "model.layers.25.self_attn.q_proj.zeros", "model.layers.25.self_attn.k_proj.zeros", "model.layers.25.self_attn.v_proj.zeros", "model.layers.25.self_attn.o_proj.zeros", "model.layers.25.mlp.gate_proj.zeros", "model.layers.25.mlp.down_proj.zeros", "model.layers.25.mlp.up_proj.zeros", "model.layers.26.self_attn.q_proj.zeros", "model.layers.26.self_attn.k_proj.zeros", "model.layers.26.self_attn.v_proj.zeros", "model.layers.26.self_attn.o_proj.zeros", "model.layers.26.mlp.gate_proj.zeros", "model.layers.26.mlp.down_proj.zeros", "model.layers.26.mlp.up_proj.zeros", "model.layers.27.self_attn.q_proj.zeros", "model.layers.27.self_attn.k_proj.zeros", "model.layers.27.self_attn.v_proj.zeros", "model.layers.27.self_attn.o_proj.zeros", "model.layers.27.mlp.gate_proj.zeros", "model.layers.27.mlp.down_proj.zeros", "model.layers.27.mlp.up_proj.zeros", "model.layers.28.self_attn.q_proj.zeros", "model.layers.28.self_attn.k_proj.zeros", "model.layers.28.self_attn.v_proj.zeros", "model.layers.28.self_attn.o_proj.zeros", "model.layers.28.mlp.gate_proj.zeros", "model.layers.28.mlp.down_proj.zeros", "model.layers.28.mlp.up_proj.zeros", "model.layers.29.self_attn.q_proj.zeros", "model.layers.29.self_attn.k_proj.zeros", "model.layers.29.self_attn.v_proj.zeros", "model.layers.29.self_attn.o_proj.zeros", "model.layers.29.mlp.gate_proj.zeros", "model.layers.29.mlp.down_proj.zeros", "model.layers.29.mlp.up_proj.zeros", "model.layers.30.self_attn.q_proj.zeros", "model.layers.30.self_attn.k_proj.zeros", "model.layers.30.self_attn.v_proj.zeros", "model.layers.30.self_attn.o_proj.zeros", "model.layers.30.mlp.gate_proj.zeros", "model.layers.30.mlp.down_proj.zeros", "model.layers.30.mlp.up_proj.zeros", "model.layers.31.self_attn.q_proj.zeros", "model.layers.31.self_attn.k_proj.zeros", "model.layers.31.self_attn.v_proj.zeros", "model.layers.31.self_attn.o_proj.zeros", "model.layers.31.mlp.gate_proj.zeros", "model.layers.31.mlp.down_proj.zeros", "model.layers.31.mlp.up_proj.zeros".
  16. Unexpected key(s) in state_dict: "model.layers.0.self_attn.q_proj.qzeros", "model.layers.0.self_attn.k_proj.qzeros", "model.layers.0.self_attn.v_proj.qzeros", "model.layers.0.self_attn.o_proj.qzeros", "model.layers.0.mlp.gate_proj.qzeros", "model.layers.0.mlp.down_proj.qzeros", "model.layers.0.mlp.up_proj.qzeros", "model.layers.1.self_attn.q_proj.qzeros", "model.layers.1.self_attn.k_proj.qzeros", "model.layers.1.self_attn.v_proj.qzeros", "model.layers.1.self_attn.o_proj.qzeros", "model.layers.1.mlp.gate_proj.qzeros", "model.layers.1.mlp.down_proj.qzeros", "model.layers.1.mlp.up_proj.qzeros", "model.layers.2.self_attn.q_proj.qzeros", "model.layers.2.self_attn.k_proj.qzeros", "model.layers.2.self_attn.v_proj.qzeros", "model.layers.2.self_attn.o_proj.qzeros", "model.layers.2.mlp.gate_proj.qzeros", "model.layers.2.mlp.down_proj.qzeros", "model.layers.2.mlp.up_proj.qzeros", "model.layers.3.self_attn.q_proj.qzeros", "model.layers.3.self_attn.k_proj.qzeros", "model.layers.3.self_attn.v_proj.qzeros", "model.layers.3.self_attn.o_proj.qzeros", "model.layers.3.mlp.gate_proj.qzeros", "model.layers.3.mlp.down_proj.qzeros", "model.layers.3.mlp.up_proj.qzeros", "model.layers.4.self_attn.q_proj.qzeros", "model.layers.4.self_attn.k_proj.qzeros", "model.layers.4.self_attn.v_proj.qzeros", "model.layers.4.self_attn.o_proj.qzeros", "model.layers.4.mlp.gate_proj.qzeros", "model.layers.4.mlp.down_proj.qzeros", "model.layers.4.mlp.up_proj.qzeros", "model.layers.5.self_attn.q_proj.qzeros", "model.layers.5.self_attn.k_proj.qzeros", "model.layers.5.self_attn.v_proj.qzeros", "model.layers.5.self_attn.o_proj.qzeros", "model.layers.5.mlp.gate_proj.qzeros", "model.layers.5.mlp.down_proj.qzeros", "model.layers.5.mlp.up_proj.qzeros", "model.layers.6.self_attn.q_proj.qzeros", "model.layers.6.self_attn.k_proj.qzeros", "model.layers.6.self_attn.v_proj.qzeros", "model.layers.6.self_attn.o_proj.qzeros", "model.layers.6.mlp.gate_proj.qzeros", "model.layers.6.mlp.down_proj.qzeros", "model.layers.6.mlp.up_proj.qzeros", "model.layers.7.self_attn.q_proj.qzeros", "model.layers.7.self_attn.k_proj.qzeros", "model.layers.7.self_attn.v_proj.qzeros", "model.layers.7.self_attn.o_proj.qzeros", "model.layers.7.mlp.gate_proj.qzeros", "model.layers.7.mlp.down_proj.qzeros", "model.layers.7.mlp.up_proj.qzeros", "model.layers.8.self_attn.q_proj.qzeros", "model.layers.8.self_attn.k_proj.qzeros", "model.layers.8.self_attn.v_proj.qzeros", "model.layers.8.self_attn.o_proj.qzeros", "model.layers.8.mlp.gate_proj.qzeros", "model.layers.8.mlp.down_proj.qzeros", "model.layers.8.mlp.up_proj.qzeros", "model.layers.9.self_attn.q_proj.qzeros", "model.layers.9.self_attn.k_proj.qzeros", "model.layers.9.self_attn.v_proj.qzeros", "model.layers.9.self_attn.o_proj.qzeros", "model.layers.9.mlp.gate_proj.qzeros", "model.layers.9.mlp.down_proj.qzeros", "model.layers.9.mlp.up_proj.qzeros", "model.layers.10.self_attn.q_proj.qzeros", "model.layers.10.self_attn.k_proj.qzeros", "model.layers.10.self_attn.v_proj.qzeros", "model.layers.10.self_attn.o_proj.qzeros", "model.layers.10.mlp.gate_proj.qzeros", "model.layers.10.mlp.down_proj.qzeros", "model.layers.10.mlp.up_proj.qzeros", "model.layers.11.self_attn.q_proj.qzeros", "model.layers.11.self_attn.k_proj.qzeros", "model.layers.11.self_attn.v_proj.qzeros", "model.layers.11.self_attn.o_proj.qzeros", "model.layers.11.mlp.gate_proj.qzeros", "model.layers.11.mlp.down_proj.qzeros", "model.layers.11.mlp.up_proj.qzeros", "model.layers.12.self_attn.q_proj.qzeros", "model.layers.12.self_attn.k_proj.qzeros", "model.layers.12.self_attn.v_proj.qzeros", "model.layers.12.self_attn.o_proj.qzeros", "model.layers.12.mlp.gate_proj.qzeros", "model.layers.12.mlp.down_proj.qzeros", "model.layers.12.mlp.up_proj.qzeros", "model.layers.13.self_attn.q_proj.qzeros", "model.layers.13.self_attn.k_proj.qzeros", "model.layers.13.self_attn.v_proj.qzeros", "model.layers.13.self_attn.o_proj.qzeros", "model.layers.13.mlp.gate_proj.qzeros", "model.layers.13.mlp.down_proj.qzeros", "model.layers.13.mlp.up_proj.qzeros", "model.layers.14.self_attn.q_proj.qzeros", "model.layers.14.self_attn.k_proj.qzeros", "model.layers.14.self_attn.v_proj.qzeros", "model.layers.14.self_attn.o_proj.qzeros", "model.layers.14.mlp.gate_proj.qzeros", "model.layers.14.mlp.down_proj.qzeros", "model.layers.14.mlp.up_proj.qzeros", "model.layers.15.self_attn.q_proj.qzeros", "model.layers.15.self_attn.k_proj.qzeros", "model.layers.15.self_attn.v_proj.qzeros", "model.layers.15.self_attn.o_proj.qzeros", "model.layers.15.mlp.gate_proj.qzeros", "model.layers.15.mlp.down_proj.qzeros", "model.layers.15.mlp.up_proj.qzeros", "model.layers.16.self_attn.q_proj.qzeros", "model.layers.16.self_attn.k_proj.qzeros", "model.layers.16.self_attn.v_proj.qzeros", "model.layers.16.self_attn.o_proj.qzeros", "model.layers.16.mlp.gate_proj.qzeros", "model.layers.16.mlp.down_proj.qzeros", "model.layers.16.mlp.up_proj.qzeros", "model.layers.17.self_attn.q_proj.qzeros", "model.layers.17.self_attn.k_proj.qzeros", "model.layers.17.self_attn.v_proj.qzeros", "model.layers.17.self_attn.o_proj.qzeros", "model.layers.17.mlp.gate_proj.qzeros", "model.layers.17.mlp.down_proj.qzeros", "model.layers.17.mlp.up_proj.qzeros", "model.layers.18.self_attn.q_proj.qzeros", "model.layers.18.self_attn.k_proj.qzeros", "model.layers.18.self_attn.v_proj.qzeros", "model.layers.18.self_attn.o_proj.qzeros", "model.layers.18.mlp.gate_proj.qzeros", "model.layers.18.mlp.down_proj.qzeros", "model.layers.18.mlp.up_proj.qzeros", "model.layers.19.self_attn.q_proj.qzeros", "model.layers.19.self_attn.k_proj.qzeros", "model.layers.19.self_attn.v_proj.qzeros", "model.layers.19.self_attn.o_proj.qzeros", "model.layers.19.mlp.gate_proj.qzeros", "model.layers.19.mlp.down_proj.qzeros", "model.layers.19.mlp.up_proj.qzeros", "model.layers.20.self_attn.q_proj.qzeros", "model.layers.20.self_attn.k_proj.qzeros", "model.layers.20.self_attn.v_proj.qzeros", "model.layers.20.self_attn.o_proj.qzeros", "model.layers.20.mlp.gate_proj.qzeros", "model.layers.20.mlp.down_proj.qzeros", "model.layers.20.mlp.up_proj.qzeros", "model.layers.21.self_attn.q_proj.qzeros", "model.layers.21.self_attn.k_proj.qzeros", "model.layers.21.self_attn.v_proj.qzeros", "model.layers.21.self_attn.o_proj.qzeros", "model.layers.21.mlp.gate_proj.qzeros", "model.layers.21.mlp.down_proj.qzeros", "model.layers.21.mlp.up_proj.qzeros", "model.layers.22.self_attn.q_proj.qzeros", "model.layers.22.self_attn.k_proj.qzeros", "model.layers.22.self_attn.v_proj.qzeros", "model.layers.22.self_attn.o_proj.qzeros", "model.layers.22.mlp.gate_proj.qzeros", "model.layers.22.mlp.down_proj.qzeros", "model.layers.22.mlp.up_proj.qzeros", "model.layers.23.self_attn.q_proj.qzeros", "model.layers.23.self_attn.k_proj.qzeros", "model.layers.23.self_attn.v_proj.qzeros", "model.layers.23.self_attn.o_proj.qzeros", "model.layers.23.mlp.gate_proj.qzeros", "model.layers.23.mlp.down_proj.qzeros", "model.layers.23.mlp.up_proj.qzeros", "model.layers.24.self_attn.q_proj.qzeros", "model.layers.24.self_attn.k_proj.qzeros", "model.layers.24.self_attn.v_proj.qzeros", "model.layers.24.self_attn.o_proj.qzeros", "model.layers.24.mlp.gate_proj.qzeros", "model.layers.24.mlp.down_proj.qzeros", "model.layers.24.mlp.up_proj.qzeros", "model.layers.25.self_attn.q_proj.qzeros", "model.layers.25.self_attn.k_proj.qzeros", "model.layers.25.self_attn.v_proj.qzeros", "model.layers.25.self_attn.o_proj.qzeros", "model.layers.25.mlp.gate_proj.qzeros", "model.layers.25.mlp.down_proj.qzeros", "model.layers.25.mlp.up_proj.qzeros", "model.layers.26.self_attn.q_proj.qzeros", "model.layers.26.self_attn.k_proj.qzeros", "model.layers.26.self_attn.v_proj.qzeros", "model.layers.26.self_attn.o_proj.qzeros", "model.layers.26.mlp.gate_proj.qzeros", "model.layers.26.mlp.down_proj.qzeros", "model.layers.26.mlp.up_proj.qzeros", "model.layers.27.self_attn.q_proj.qzeros", "model.layers.27.self_attn.k_proj.qzeros", "model.layers.27.self_attn.v_proj.qzeros", "model.layers.27.self_attn.o_proj.qzeros", "model.layers.27.mlp.gate_proj.qzeros", "model.layers.27.mlp.down_proj.qzeros", "model.layers.27.mlp.up_proj.qzeros", "model.layers.28.self_attn.q_proj.qzeros", "model.layers.28.self_attn.k_proj.qzeros", "model.layers.28.self_attn.v_proj.qzeros", "model.layers.28.self_attn.o_proj.qzeros", "model.layers.28.mlp.gate_proj.qzeros", "model.layers.28.mlp.down_proj.qzeros", "model.layers.28.mlp.up_proj.qzeros", "model.layers.29.self_attn.q_proj.qzeros", "model.layers.29.self_attn.k_proj.qzeros", "model.layers.29.self_attn.v_proj.qzeros", "model.layers.29.self_attn.o_proj.qzeros", "model.layers.29.mlp.gate_proj.qzeros", "model.layers.29.mlp.down_proj.qzeros", "model.layers.29.mlp.up_proj.qzeros", "model.layers.30.self_attn.q_proj.qzeros", "model.layers.30.self_attn.k_proj.qzeros", "model.layers.30.self_attn.v_proj.qzeros", "model.layers.30.self_attn.o_proj.qzeros", "model.layers.30.mlp.gate_proj.qzeros", "model.layers.30.mlp.down_proj.qzeros", "model.layers.30.mlp.up_proj.qzeros", "model.layers.31.self_attn.q_proj.qzeros", "model.layers.31.self_attn.k_proj.qzeros", "model.layers.31.self_attn.v_proj.qzeros", "model.layers.31.self_attn.o_proj.qzeros", "model.layers.31.mlp.gate_proj.qzeros", "model.layers.31.mlp.down_proj.qzeros", "model.layers.31.mlp.up_proj.qzeros".
  17. size mismatch for model.layers.0.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  18. size mismatch for model.layers.0.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  19. size mismatch for model.layers.0.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  20. size mismatch for model.layers.0.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  21. size mismatch for model.layers.0.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  22. size mismatch for model.layers.0.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  23. size mismatch for model.layers.0.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  24. size mismatch for model.layers.1.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  25. size mismatch for model.layers.1.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  26. size mismatch for model.layers.1.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  27. size mismatch for model.layers.1.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  28. size mismatch for model.layers.1.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  29. size mismatch for model.layers.1.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  30. size mismatch for model.layers.1.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  31. size mismatch for model.layers.2.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  32. size mismatch for model.layers.2.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  33. size mismatch for model.layers.2.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  34. size mismatch for model.layers.2.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  35. size mismatch for model.layers.2.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  36. size mismatch for model.layers.2.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  37. size mismatch for model.layers.2.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  38. size mismatch for model.layers.3.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  39. size mismatch for model.layers.3.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  40. size mismatch for model.layers.3.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  41. size mismatch for model.layers.3.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  42. size mismatch for model.layers.3.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  43. size mismatch for model.layers.3.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  44. size mismatch for model.layers.3.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  45. size mismatch for model.layers.4.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  46. size mismatch for model.layers.4.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  47. size mismatch for model.layers.4.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  48. size mismatch for model.layers.4.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  49. size mismatch for model.layers.4.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  50. size mismatch for model.layers.4.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  51. size mismatch for model.layers.4.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  52. size mismatch for model.layers.5.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  53. size mismatch for model.layers.5.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  54. size mismatch for model.layers.5.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  55. size mismatch for model.layers.5.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  56. size mismatch for model.layers.5.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  57. size mismatch for model.layers.5.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  58. size mismatch for model.layers.5.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  59. size mismatch for model.layers.6.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  60. size mismatch for model.layers.6.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  61. size mismatch for model.layers.6.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  62. size mismatch for model.layers.6.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  63. size mismatch for model.layers.6.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  64. size mismatch for model.layers.6.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  65. size mismatch for model.layers.6.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  66. size mismatch for model.layers.7.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  67. size mismatch for model.layers.7.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  68. size mismatch for model.layers.7.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  69. size mismatch for model.layers.7.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  70. size mismatch for model.layers.7.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  71. size mismatch for model.layers.7.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  72. size mismatch for model.layers.7.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  73. size mismatch for model.layers.8.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  74. size mismatch for model.layers.8.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  75. size mismatch for model.layers.8.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  76. size mismatch for model.layers.8.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  77. size mismatch for model.layers.8.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  78. size mismatch for model.layers.8.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  79. size mismatch for model.layers.8.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  80. size mismatch for model.layers.9.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  81. size mismatch for model.layers.9.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  82. size mismatch for model.layers.9.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  83. size mismatch for model.layers.9.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  84. size mismatch for model.layers.9.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  85. size mismatch for model.layers.9.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  86. size mismatch for model.layers.9.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  87. size mismatch for model.layers.10.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  88. size mismatch for model.layers.10.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  89. size mismatch for model.layers.10.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  90. size mismatch for model.layers.10.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  91. size mismatch for model.layers.10.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  92. size mismatch for model.layers.10.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  93. size mismatch for model.layers.10.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  94. size mismatch for model.layers.11.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  95. size mismatch for model.layers.11.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  96. size mismatch for model.layers.11.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  97. size mismatch for model.layers.11.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  98. size mismatch for model.layers.11.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  99. size mismatch for model.layers.11.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  100. size mismatch for model.layers.11.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  101. size mismatch for model.layers.12.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  102. size mismatch for model.layers.12.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  103. size mismatch for model.layers.12.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  104. size mismatch for model.layers.12.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  105. size mismatch for model.layers.12.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  106. size mismatch for model.layers.12.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  107. size mismatch for model.layers.12.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  108. size mismatch for model.layers.13.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  109. size mismatch for model.layers.13.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  110. size mismatch for model.layers.13.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  111. size mismatch for model.layers.13.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  112. size mismatch for model.layers.13.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  113. size mismatch for model.layers.13.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  114. size mismatch for model.layers.13.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  115. size mismatch for model.layers.14.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  116. size mismatch for model.layers.14.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  117. size mismatch for model.layers.14.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  118. size mismatch for model.layers.14.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  119. size mismatch for model.layers.14.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  120. size mismatch for model.layers.14.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  121. size mismatch for model.layers.14.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  122. size mismatch for model.layers.15.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  123. size mismatch for model.layers.15.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  124. size mismatch for model.layers.15.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  125. size mismatch for model.layers.15.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  126. size mismatch for model.layers.15.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  127. size mismatch for model.layers.15.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  128. size mismatch for model.layers.15.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  129. size mismatch for model.layers.16.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  130. size mismatch for model.layers.16.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  131. size mismatch for model.layers.16.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  132. size mismatch for model.layers.16.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  133. size mismatch for model.layers.16.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  134. size mismatch for model.layers.16.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  135. size mismatch for model.layers.16.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  136. size mismatch for model.layers.17.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  137. size mismatch for model.layers.17.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  138. size mismatch for model.layers.17.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  139. size mismatch for model.layers.17.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  140. size mismatch for model.layers.17.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  141. size mismatch for model.layers.17.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  142. size mismatch for model.layers.17.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  143. size mismatch for model.layers.18.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  144. size mismatch for model.layers.18.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  145. size mismatch for model.layers.18.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  146. size mismatch for model.layers.18.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  147. size mismatch for model.layers.18.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  148. size mismatch for model.layers.18.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  149. size mismatch for model.layers.18.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  150. size mismatch for model.layers.19.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  151. size mismatch for model.layers.19.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  152. size mismatch for model.layers.19.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  153. size mismatch for model.layers.19.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  154. size mismatch for model.layers.19.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  155. size mismatch for model.layers.19.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  156. size mismatch for model.layers.19.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  157. size mismatch for model.layers.20.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  158. size mismatch for model.layers.20.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  159. size mismatch for model.layers.20.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  160. size mismatch for model.layers.20.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  161. size mismatch for model.layers.20.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  162. size mismatch for model.layers.20.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  163. size mismatch for model.layers.20.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  164. size mismatch for model.layers.21.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  165. size mismatch for model.layers.21.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  166. size mismatch for model.layers.21.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  167. size mismatch for model.layers.21.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  168. size mismatch for model.layers.21.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  169. size mismatch for model.layers.21.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  170. size mismatch for model.layers.21.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  171. size mismatch for model.layers.22.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  172. size mismatch for model.layers.22.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  173. size mismatch for model.layers.22.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  174. size mismatch for model.layers.22.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  175. size mismatch for model.layers.22.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  176. size mismatch for model.layers.22.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  177. size mismatch for model.layers.22.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  178. size mismatch for model.layers.23.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  179. size mismatch for model.layers.23.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  180. size mismatch for model.layers.23.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  181. size mismatch for model.layers.23.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  182. size mismatch for model.layers.23.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  183. size mismatch for model.layers.23.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  184. size mismatch for model.layers.23.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  185. size mismatch for model.layers.24.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  186. size mismatch for model.layers.24.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  187. size mismatch for model.layers.24.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  188. size mismatch for model.layers.24.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  189. size mismatch for model.layers.24.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  190. size mismatch for model.layers.24.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  191. size mismatch for model.layers.24.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  192. size mismatch for model.layers.25.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  193. size mismatch for model.layers.25.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  194. size mismatch for model.layers.25.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  195. size mismatch for model.layers.25.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  196. size mismatch for model.layers.25.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  197. size mismatch for model.layers.25.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  198. size mismatch for model.layers.25.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  199. size mismatch for model.layers.26.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  200. size mismatch for model.layers.26.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  201. size mismatch for model.layers.26.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  202. size mismatch for model.layers.26.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  203. size mismatch for model.layers.26.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  204. size mismatch for model.layers.26.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  205. size mismatch for model.layers.26.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  206. size mismatch for model.layers.27.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  207. size mismatch for model.layers.27.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  208. size mismatch for model.layers.27.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  209. size mismatch for model.layers.27.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  210. size mismatch for model.layers.27.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  211. size mismatch for model.layers.27.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  212. size mismatch for model.layers.27.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  213. size mismatch for model.layers.28.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  214. size mismatch for model.layers.28.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  215. size mismatch for model.layers.28.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  216. size mismatch for model.layers.28.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  217. size mismatch for model.layers.28.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  218. size mismatch for model.layers.28.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  219. size mismatch for model.layers.28.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  220. size mismatch for model.layers.29.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  221. size mismatch for model.layers.29.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  222. size mismatch for model.layers.29.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  223. size mismatch for model.layers.29.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  224. size mismatch for model.layers.29.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  225. size mismatch for model.layers.29.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  226. size mismatch for model.layers.29.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  227. size mismatch for model.layers.30.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  228. size mismatch for model.layers.30.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  229. size mismatch for model.layers.30.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  230. size mismatch for model.layers.30.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  231. size mismatch for model.layers.30.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  232. size mismatch for model.layers.30.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  233. size mismatch for model.layers.30.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  234. size mismatch for model.layers.31.self_attn.q_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  235. size mismatch for model.layers.31.self_attn.k_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  236. size mismatch for model.layers.31.self_attn.v_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  237. size mismatch for model.layers.31.self_attn.o_proj.scales: copying a param with shape torch.Size([32, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  238. size mismatch for model.layers.31.mlp.gate_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
  239. size mismatch for model.layers.31.mlp.down_proj.scales: copying a param with shape torch.Size([86, 4096]) from checkpoint, the shape in current model is torch.Size([4096, 1]).
  240. size mismatch for model.layers.31.mlp.up_proj.scales: copying a param with shape torch.Size([32, 11008]) from checkpoint, the shape in current model is torch.Size([11008, 1]).
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!