Loading local .pt file with from_pretrained failes cause of domino chain of errors.

[gilkzxc]

By using the "http://one-peace-shanghai.oss-accelerate.aliyuncs.com/one-peace.pt", and from_pretrained().
I failed to load the pretrained model.
As it's prints "Killed".
So I have traced deeper to the location of the bug.
Led me to try checkpoint_utils.load_model_ensemble_and_task(), which also failed.
Eventually, I have found that an AssertionError is been raised in line 43 setup_task()
"task is not None"

[logicwong]

It might be because you haven't installed fairseq under this repo. Try:

pip uninstall fairseq
git clone https://github.com/OFA-Sys/ONE-PEACE
cd ONE-PEACE
pip install -r requirements.txt

[gilkzxc]

But I did install fairseq in the same directory.

[logicwong]

Can you share your execution command?

[gilkzxc]

That's just shows "Killed".
So I used the equivalent calls that from_pretraind() do. And then load_model.... and etc..

[logicwong]

Could it be because there's not enough memory? Try this:
model = from_pretrained("one-peace.pt", device=device, dtype="float16")

[gilkzxc]

Tried with dtype="float16" and "float8", same result "Killed".

[gilkzxc]

Even reinstalled omegaconf again to be sure it's 2.0.6 as required.

[logicwong]

Can you switch to a machine with larger memory, and then try using model = from_pretrained("one-peace.pt", device='cpu', dtype="float16")? I haven't encountered this situation before.