-
Notifications
You must be signed in to change notification settings - Fork 722
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
How to use 1.3B OPT weights in metaseq-api-local
API?
#61
Comments
You can modify the paths manually to load different models. Also, I think this script is related. |
@soloice I know that we can modify path to load different models. My question is |
I have the same question. I assume this is not a bug: the only thing missing here is a script to merge all sharded checkpoints. |
I guess there is a way to directly load two reshard file (and infer under the strategy of model paralleling) rather than merging them. |
I'm trying to use 1.3B OPT weights in
metaseq-api-local
API and test some inference examples. But I got stucked.There are two reshard files of 1.3B OPT. But
CHECKPOINT_LOCAL
inconstants.py
can only point to areshard.pt
file. What is the correct way to load these two reshard files? (P.S. the comments inconstants.py
saysMODEL_SHARED_FOLDER = "/example/175B/reshard_no_os"
but there isCHECKPOINT_FOLDER = os.path.join(MODEL_SHARED_FOLDER, "175B", "reshard_no_os")
in line 49, is this also a mistake?The text was updated successfully, but these errors were encountered: