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.

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

微调qwen2.5 3B模型报“UnicodeDecodeError”错误,请作者帮忙看看,谢谢! #5875

Open
1 task done
yangdy11111 opened this issue Oct 30, 2024 · 0 comments
Labels
pending This problem is yet to be addressed

Comments

@yangdy11111
Copy link

Reminder

  • I have read the README and searched the existing issues.

System Info

  • llamafactory version: 0.9.1.dev0
  • Platform: Windows-10-10.0.26100-SP0
  • Python version: 3.11.10
  • PyTorch version: 2.1.0+cu118 (GPU)
  • Transformers version: 4.45.2
  • Datasets version: 2.21.0
  • Accelerate version: 0.34.2
  • PEFT version: 0.11.1
  • TRL version: 0.9.6
  • GPU type: NVIDIA GeForce RTX 3070

Reproduction

[INFO|trainer.py:3705] 2024-10-30 18:25:14,361 >> Saving model checkpoint to ./saves/qwen2.5
Traceback (most recent call last):
File "", line 198, in _run_module_as_main
File "", line 88, in run_code
File "C:\Users\aaa\anaconda3\envs\llamafac\Scripts\llamafactory-cli.exe_main
.py", line 7, in
File "C:\Users\aaa\Desktop\llamafac\src\llamafactory\cli.py", line 111, in main
run_exp()
File "C:\Users\aaa\Desktop\llamafac\src\llamafactory\train\tuner.py", line 50, in run_exp
run_sft(model_args, data_args, training_args, finetuning_args, generating_args, callbacks)
File "C:\Users\aaa\Desktop\llamafac\src\llamafactory\train\sft\workflow.py", line 97, in run_sft
trainer.save_model()
File "C:\Users\aaa\anaconda3\envs\llamafac\Lib\site-packages\transformers\trainer.py", line 3623, in save_model
self._save(output_dir)
File "C:\Users\aaa\anaconda3\envs\llamafac\Lib\site-packages\transformers\trainer.py", line 3727, in _save
self.model.save_pretrained(
File "C:\Users\aaa\anaconda3\envs\llamafac\Lib\site-packages\peft\peft_model.py", line 246, in save_pretrained
self.create_or_update_model_card(save_directory)
File "C:\Users\aaa\anaconda3\envs\llamafac\Lib\site-packages\peft\peft_model.py", line 1087, in create_or_update_model_card
card = ModelCard.load(filename) if os.path.exists(filename) else ModelCard.from_template(ModelCardData())
^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\aaa\anaconda3\envs\llamafac\Lib\site-packages\huggingface_hub\repocard.py", line 190, in load
return cls(f.read(), ignore_metadata_errors=ignore_metadata_errors)
^^^^^^^^
File "", line 322, in decode
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xb0 in position 510: invalid start byte

Expected behavior

请帮忙看看如何解决,谢谢!

Others

No response

@github-actions github-actions bot added the pending This problem is yet to be addressed label Oct 30, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
pending This problem is yet to be addressed
Projects
None yet
Development

No branches or pull requests

1 participant