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

Original tensorflow checkpoints #1

Open
ccclyu opened this issue Aug 19, 2020 · 0 comments
Open

Original tensorflow checkpoints #1

ccclyu opened this issue Aug 19, 2020 · 0 comments

Comments

@ccclyu
Copy link

ccclyu commented Aug 19, 2020

Thanks for your nice work ! I am conducting experiments by loading your pretrained "2 Million MLM+NSP steps LIBERT checkpoint" but I found it only includes the "BERT" parameters without any parameters from the lexical similarity task. May I have your original tensorflow checkpoints, i.e., including the following two parameters?

https://github.com/anlausch/LIBERT/blob/master/code/run_pretraining_libert.py#L312-L317

 with tf.variable_scope("wordnet"):
    output_weights = tf.get_variable(
      "output_weights", [num_labels, hidden_size],
        initializer=tf.truncated_normal_initializer(stddev=0.02))
    output_bias = tf.get_variable(
      "output_bias", [num_labels], initializer=tf.zeros_initializer())

Would greatly appreciate if you could share with me.

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

1 participant