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

link to download model is broken #13

Open
Avi-avidan opened this issue Nov 9, 2020 · 6 comments
Open

link to download model is broken #13

Avi-avidan opened this issue Nov 9, 2020 · 6 comments

Comments

@Avi-avidan
Copy link

hi, loved the repo.
link to download the model appears broken.
can you update?
thanks, a.

@kamalkraj
Copy link
Owner

https://huggingface.co/bert-large-uncased-whole-word-masking-finetuned-squad
You can download the model from the above link. You will have to rename the config.json to bert_config.json

@kamalkraj
Copy link
Owner

Using

model =QA('bert-large-uncased-whole-word-masking-finetuned-squad')

Will also work.

@soumya997
Copy link

soumya997 commented Nov 14, 2020

@kamalkraj I have not tried the model yet, but can you please clarify a point,
If I use this code,

from bert import QA
model = QA('bert-large-uncased-whole-word-masking-finetuned-squad')

then it will download the model, right?

So, If I need to save the model then what should I do?

@kamalkraj
Copy link
Owner

@soumya997
The model will be downloaded and cached. The model downloaded only during the first run. The second run onwards it loads from the cache.

@soumya997
Copy link

Oh, thank you @kamalkraj for the clarification.
Another thing that I wanted to ask you.
You have an implementation of minGPT in tf 2.x, I used that code to train my joke generation model.
can you please tell me how can I save that model?

@kamalkraj
Copy link
Owner

@soumya997
Pass the ckpt_path to TrainerConfig. The model will be saved after each epoch.

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