I am trying to use "python convert.py models/7B/" command to convert my model to ggml FP16 format.
Models and 7B folders contain the following files;
models/
├── 7B
│ ├── checklist.chk
│ ├── consolidated.00.pth
│ └── params.json
├── tokenizer.model
└── tokenizer_checklist.chk
When I run the command I get the "zipfile.BadZipFile: Bad magic number for file header" error. I've tried to tinker with the "convert.py" file but I couldn't manage to solve the problem. Does anyone know what might cause the issue and how can I fix it?
I am using Python version 3.9 with the requirements( found in requirements.txt in llama.cpp file) installed.