matteogeniaccio

/

phi-4

like 54

I’m trying to convert the model weights on my own, but I keep getting this error. =( Could it be that the tokenizer.model file is missing, or am I doing something wrong?

INFO:hf-to-gguf:Set model tokenizer
Traceback (most recent call last):
  File "C:\Users\User\Documents\GitHub\llama.cpp\convert_hf_to_gguf.py", line 4462, in <module>
    main()
  File "C:\Users\User\Documents\GitHub\llama.cpp\convert_hf_to_gguf.py", line 4456, in main
    model_instance.write()
  File "C:\Users\User\Documents\GitHub\llama.cpp\convert_hf_to_gguf.py", line 435, in write
    self.prepare_metadata(vocab_only=False)
  File "C:\Users\User\Documents\GitHub\llama.cpp\convert_hf_to_gguf.py", line 428, in prepare_metadata
    self.set_vocab()
  File "C:\Users\User\Documents\GitHub\llama.cpp\convert_hf_to_gguf.py", line 2137, in set_vocab
    raise ValueError(f'Error: Missing {tokenizer_path}')
ValueError: Error: Missing F:\Models\phi-4\tokenizer.model