python3 convert-hf-to-ggml.py bigcode/starcoderplus is failing with error: RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory
antonakv opened this issue · 1 comments
antonakv commented
python3 convert-hf-to-ggml.py bigcode/starcoderplus
is failing with error: RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory
% python3 convert-hf-to-ggml.py models/starcoderplus
Loading model: models/starcoderplus
Loading checkpoint shards: 29%|█████████████████████████████████████▍ | 2/7 [00:45<01:54, 22.80s/it]
Traceback (most recent call last):
File "/starcoder.cpp/venv/lib/python3.11/site-packages/transformers/modeling_utils.py", line 460, in load_state_dict
return torch.load(checkpoint_file, map_location="cpu")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/starcoder.cpp/venv/lib/python3.11/site-packages/torch/serialization.py", line 797, in load
with _open_zipfile_reader(opened_file) as opened_zipfile:
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/starcoder.cpp/venv/lib/python3.11/site-packages/torch/serialization.py", line 283, in __init__
super().__init__(torch._C.PyTorchFileReader(name_or_buffer))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/starcoder.cpp/venv/lib/python3.11/site-packages/transformers/modeling_utils.py", line 464, in load_state_dict
if f.read(7) == "version":
^^^^^^^^^
File "<frozen codecs>", line 322, in decode
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 128: invalid start byte
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/starcoder.cpp/convert-hf-to-ggml.py", line 58, in <module>
model = AutoModelForCausalLM.from_pretrained(model_name, config=config, torch_dtype=torch.float16 if use_f16 else torch.float32, low_cpu_mem_usage=True, trust_remote_code=True, offload_state_dict=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/starcoder.cpp/venv/lib/python3.11/site-packages/transformers/models/auto/auto_factory.py", line 493, in from_pretrained
return model_class.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/starcoder.cpp/venv/lib/python3.11/site-packages/transformers/modeling_utils.py", line 2903, in from_pretrained
) = cls._load_pretrained_model(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/starcoder.cpp/venv/lib/python3.11/site-packages/transformers/modeling_utils.py", line 3246, in _load_pretrained_model
state_dict = load_state_dict(shard_file)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/starcoder.cpp/venv/lib/python3.11/site-packages/transformers/modeling_utils.py", line 476, in load_state_dict
raise OSError(
OSError: Unable to load weights from pytorch checkpoint file for 'models/starcoderplus/pytorch_model-00003-of-00007.bin' at 'models/starcoderplus/pytorch_model-00003-of-00007.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.
Installed python packages:
% pip3 list
Package Version
------------------ ---------
accelerate 0.21.0
certifi 2023.7.22
charset-normalizer 3.2.0
filelock 3.12.2
fsspec 2023.6.0
huggingface 0.0.1
huggingface-hub 0.16.4
idna 3.4
Jinja2 3.1.2
MarkupSafe 2.1.3
mpmath 1.3.0
networkx 3.1
numpy 1.25.1
packaging 23.1
pip 23.0.1
psutil 5.9.5
PyYAML 6.0.1
regex 2023.6.3
requests 2.31.0
safetensors 0.3.1
setuptools 67.6.1
starcoder 0.0.2
sympy 1.12
tokenizers 0.13.3
torch 2.0.1
tqdm 4.65.0
transformers 4.31.0
typing_extensions 4.7.1
urllib3 2.0.4
MexHigh commented
Same problem here