[go: up one dir, main page]

Skip to content
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

Finetuning with hugging face models not working for evaluate #81

Open
YanSoares opened this issue Dec 27, 2022 · 2 comments
Open

Finetuning with hugging face models not working for evaluate #81

YanSoares opened this issue Dec 27, 2022 · 2 comments

Comments

@YanSoares
Copy link

from neuspell import BertChecker

checker = BertChecker()
checker.from_pretrained(
bert_pretrained_name_or_path="distilbert-base-cased",
ckpt_path=f"{data_dir}/new_models/distilbert-base-cased" # ""
)
checker.evaluate(clean_file=clean_file, corrupt_file=corrupt_file, data_dir=data_dir)

ERROR NUM 1: TypeError: _from_pretrained() got an unexpected keyword argument 'bert_pretrained_name_or_path'
ERROR NUM 2: When comment this line, we get a new error: _pickle.UnpicklingError: invalid load key, '<'.

it seems that the trained model is not being loaded correctly, can you help me?

@vignesh-fynd
Copy link

Any solution on this issue, I am also facing the same?

@KSSSenapati
Copy link

#36 (comment)

@YanSoares @vignesh-fynd Please refer to this comment for solving this issue
Similarly, for other models you can use the checkpoints from here - https://drive.google.com/drive/folders/1jgNpYe4TVSF4mMBVtFh4QfB2GovNPdh7

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants