Skip to content

regression: convert.py Could not find any of ['vocab.json'] for deepseek-coder models (--pad-vocab --vocab-type bpe) #5973

Closed
@0x4E69676874466F78

Description

@0x4E69676874466F78

Regression commit 4d4d236

python.exe convert.py --outtype f32 --pad-vocab --vocab-type bpe B:\deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code
...
Found vocab files: {'spm': None, 'bpe': None, 'hfft': WindowsPath('B:/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code/tokenizer.json')}
Traceback (most recent call last):
  File "A:\gitproject\llama.cpp\convert.py", line 1479, in <module>
    main()
  File "A:\gitproject\llama.cpp\convert.py", line 1447, in main
    vocab, special_vocab = vocab_factory.load_vocab(args.vocab_type.split(","), model_parent_path)
  File "A:\gitproject\llama.cpp\convert.py", line 1323, in load_vocab
    vocab_type, path = self._select_file(vocab_types)
  File "A:\gitproject\llama.cpp\convert.py", line 1310, in _select_file
    raise FileNotFoundError(f"Could not find any of {[self._FILES[vt] for vt in vocab_types]}")
FileNotFoundError: Could not find any of ['vocab.json']

Same with the original deepseek-coder model.

git checkout aa23412 convert.py
OK

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions