not found weight file
Cguanqin opened this issue · comments
Build the image according to the dockerfile file, then run the container. Error: IsADirectoryError: [Errno 21] Is a directory: '/tmp/ckpt', it should be that there is no weight file in the directory '/tmp/ckpt'. Did not a weight file be generated when building the image? How to solve this problem?
[root@iZwz9fjpavyfd2ybhfxx1lZ gemma_pytorch]# docker run -t --rm \
-v /tmp/ckpt:/tmp/ckpt \ gemma:pytorch \ python scripts/run.py \ --ckpt=/tmp/ckpt \ --variant="2b" \ --prompt="The meaning of life is"
Traceback (most recent call last):
File "/workspace/gemma/scripts/run.py", line 79, in
main(args)
File "/workspace/gemma/scripts/run.py", line 48, in main
model.load_weights(args.ckpt)
File "/workspace/gemma/gemma/model.py", line 562, in load_weights
torch.load(
File "/opt/conda/lib/python3.10/site-packages/torch/serialization.py", line 986, in load
with _open_file_like(f, 'rb') as opened_file:
File "/opt/conda/lib/python3.10/site-packages/torch/serialization.py", line 435, in _open_file_like
return _open_file(name_or_buffer, mode)
File "/opt/conda/lib/python3.10/site-packages/torch/serialization.py", line 416, in init
super().init(open(name, mode))
IsADirectoryError: [Errno 21] Is a directory: '/tmp/ckpt'
Hi @Cguanqin, have you downloaded the checkpoint from Kaggle or HuggingFace Hub before running the docker?
You can follow the instruction here to get the checkpoint.
https://www.kaggle.com/models/google/gemma/frameworks/pyTorch
Hi @Cguanqin, have you downloaded the checkpoint from Kaggle or HuggingFace Hub before running the docker?
You can follow the instruction here to get the checkpoint. https://www.kaggle.com/models/google/gemma/frameworks/pyTorch
I have confirmed that I have downloaded the model, but I am still encountering this error regardless of whether I specify the path where the model was downloaded or the path to the model file itself.