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

ValueError: Tokenizer class XgenTokenizer does not exist or is not currently imported. #15

Open
EuclidM17 opened this issue Jul 3, 2023 · 1 comment

Comments

@EuclidM17
Copy link

I need help.
When using model = "Salesforce/xgen-7b-4k-base" or model = "Salesforce/xgen-7b-8k-base"

/usr/local/lib/python3.10/dist-packages/transformers/models/auto/tokenization_auto.py in from_pretrained(cls, pretrained_model_name_or_path, *inputs, **kwargs)
687 tokenizer_class = tokenizer_class_from_name(tokenizer_class_candidate)
688 if tokenizer_class is None:
--> 689 raise ValueError(
690 f"Tokenizer class {tokenizer_class_candidate} does not exist or is not currently imported."
691 )

ValueError: Tokenizer class XgenTokenizer does not exist or is not currently imported.

I have this issue locally or in googla colab.

I import these :
!pip install git+https://www.github.com/huggingface/transformers
!pip install git+https://github.com/huggingface/accelerate
!pip install bitsandbytes
!pip install tiktoken

@gardner
Copy link

gardner commented Jul 15, 2023

The XgenTokenizer is defined in a python file that is included in the model repo: https://huggingface.co/Salesforce/xgen-7b-4k-base/blob/main/tokenization_xgen.py

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