8000 OSError: Can't load tokenizer for 'bert-base-uncased · Issue #12 · showlab/mist · GitHub
[go: up one dir, main page]

Skip to content
< 8000 link rel="modulepreload" href="https://github.githubassets.com/assets/84656-83eb10da3d6550df.js" crossorigin="anonymous" />

OSError: Can't load tokenizer for 'bert-base-uncased #12

Open

Description

@wpx-1

I had follow the tutorial to run the code ,the paths of data also were modified.but I can not run the code successfully. there are the error infomation.
Traceback (most recent call last):
File "/work/shared_pool_data02/multi_modal/mist/main_agqa_v2.py", line 36, in
bert_tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
File "/home/wpx/miniconda3/envs/mistenv/lib/python3.9/site-packages/transformers/tokenization_utils_base.py", line 1795, in from_pretrained
raise EnvironmentError(
OSError: Can't load tokenizer for 'bert-base-uncased'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'bert-base-uncased' is the correct path to a directory containing all relevant files for a BertTokenizer tokenizer.

Activity

  1. yangk-910 commented on Oct 27, 2023

    @yangk-910

    You can download the relevant files of the bert-base-uncased model from huggingface.co and place them in the mist/"bert-base-uncased folder, then bert_tokenizer =BertTokenizer. from_ pretrained ("./bert-base-uncased"). You can try this to see if it works, that's what I did before with the robert model.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions

      0