Skip to content

convert : fix TypeError on GPT-2 vocab.json #5288

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

Merged
merged 2 commits into from
Feb 7, 2024

Conversation

likejazz
Copy link
Contributor

@likejazz likejazz commented Feb 2, 2024

  File "/llama.cpp/convert.py", line 1474, in <module>
    main()
  File "/llama.cpp/convert.py", line 1442, in main
    vocab, special_vocab = vocab_factory.load_vocab(args.vocab_type, model_parent_path)
  File "/llama.cpp/convert.py", line 1324, in load_vocab
    vocab = BpeVocab(
  File "/llama.cpp/convert.py", line 338, in __init__
    self.vocab = self.bpe_tokenizer["model"]["vocab"]
TypeError: 'int' object is not subscriptable

The error that occurred is TypeError, so I add one more exception type.
#5194

@cebtenzzre cebtenzzre changed the title Add TypeError exception for BPE vocab. convert : fix TypeError on GPT-2 vocab.json Feb 4, 2024
@likejazz
Copy link
Contributor Author

likejazz commented Feb 7, 2024

@cebtenzzre @ggerganov When will it be merged?
Some of check failed with an error No space left on device, which is an error on GitHub's part, not mine.
https://github.com/ggerganov/llama.cpp/actions/runs/7775159375/job/21200806090?pr=5288

@cebtenzzre cebtenzzre merged commit f68664a into ggml-org:master Feb 7, 2024
jordankanter pushed a commit to jordankanter/llama.cpp that referenced this pull request Mar 13, 2024
hodlen pushed a commit to hodlen/llama.cpp that referenced this pull request Apr 1, 2024
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

Successfully merging this pull request may close these issues.

2 participants