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

Error 'HuggingLanguageModel' object has no attribute 'generate_solution' #89

Open
rkuo2000 opened this issue Feb 24, 2024 · 6 comments
Open

Comments

@rkuo2000
Copy link

rkuo2000 commented Feb 24, 2024

/opt/conda/lib/python3.10/site-packages/tree_of_thoughts/treeofthoughts.py:481
solution = self.model.generate_solution(initial_prompt, best_state)

AttributeError: 'HuggingLanguageModel' object has no attribute 'generate_solution'

Upvote & Fund

  • We're using Polar.sh so you can upvote and help fund this issue.
  • We receive the funding once the issue is completed & confirmed by you.
  • Thank you in advance for helping prioritize & fund our backlog.
Fund with Polar
@kyegomez
Copy link
Owner

@rkuo2000 try the new script on the readme

@rkuo2000
Copy link
Author

https://www.kaggle.com/code/rkuo2000/llm-tot
please check out the error messages on Kaggle

Error: '>=' not supported between instances of 'int' and 'str'

Setting pad_token_id to eos_token_id:50256 for open-end generation.

AttributeError: 'HuggingLanguageModel' object has no attribute 'generate_solution'

what script should be runned ?

@kyegomez
Copy link
Owner

Hey @rkuo2000 HuggingfaceLanguageModel doesn't exist, can you try again with the new examples on the readme ?

@rkuo2000
Copy link
Author

I am trying to run with HuggingFace free models, so Huggingface Language Model is no longer supported ?

@kyegomez
Copy link
Owner

@rkuo2000 check the example on the readme md we make big new update

@rkuo2000
Copy link
Author

rkuo2000 commented Feb 25, 2024

https://www.kaggle.com/code/rkuo2000/llm-tree-of-thoughts/notebook
(Same error occurs by running on Ubuntu 22.04 LTS PC with GPU)

HuggingfaceLLM could not generate text because of error: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument index in method wrapper_CUDA__index_select), try optimizing your arguments
2024-02-25T12:46:11.196489+0000 Error running agent: local variable 'response' referenced before assignment

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants