RuntimeError: PytorchStreamReader failed reading zip archive: not a ZIP archive

[RoversX]

Hello, I try to # convert the 7B model to ggml FP16 format but I found a problem? Is that because of the model problem? 🙏🏻

python3 convert-pth-to-ggml.py models/7B/ 1

.
├── CMakeLists.txt
├── LICENSE
├── Makefile
├── README.md
├── convert-pth-to-ggml.py
├── ggml.c
├── ggml.h
├── ggml.o
├── main
├── main.cpp
├── models
│   ├── 7B
│   │   ├── checklist.chk
│   │   ├── consolidated.00.pth
│   │   └── params.json
│   ├── tokenizer.model
│   └── tokenizer_checklist.chk
├── quantize
├── quantize.cpp
├── quantize.sh
├── utils.cpp
├── utils.h
└── utils.o

(Lab2) @-MacBook-Pro llama.cpp % python convert-pth-to-ggml.py models/7B/ 1
{'dim': 4096, 'multiple_of': 256, 'n_heads': 32, 'n_layers': 32, 'norm_eps': 1e-06, 'vocab_size': 32000}
n_parts =  1
Processing part  0
Traceback (most recent call last):
  File "Lab2/llama.cpp/convert-pth-to-ggml.py", line 88, in <module>
    model = torch.load(fname_model, map_location="cpu")
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "Lab2/lib/python3.11/site-packages/torch/serialization.py", line 799, in load
    with _open_zipfile_reader(opened_file) as opened_zipfile:
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "Lab2/lib/python3.11/site-packages/torch/serialization.py", line 285, in __init__
    super().__init__(torch._C.PyTorchFileReader(name_or_buffer))
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: PytorchStreamReader failed reading zip archive: not a ZIP archive
(Lab2) @-MacBook-Pro llama.cpp % 

[wyy912]

Same issue, and I fix it by redownload the 7B model.

meta-llama/llama#73

First time, I download by ipfs, and second time, I download by magnet, the problem was gone.

Hope it helpful

[RoversX]

Same issue, and I fix it by redownload the 7B model.

facebookresearch/llama#73

First time, I download by ipfs, and second time, I download by magnet, the problem was gone.

Hope it helpful

Wow, Thank you! It actually work!