8000 Different Vocab Size Between Tokenizer and Model's Word Embedding Layer · Issue #33 · IndoNLP/indonlu · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Different Vocab Size Between Tokenizer and Model's Word Embedding Layer #33

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.

Sign up for GitHub

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

Jump to bottom
Open
louisowen6 opened this issue Jul 23, 2021 · 0 comments
Open

Different Vocab Size Between Tokenizer and Model's Word Embedding Layer #33

louisowen6 opened this issue Jul 23, 2021 · 0 comments

Comments

@louisowen6
Copy link

Expected Behavior

The length of tokenizer vocab size and the BERT's word embedding layer dimension should be the same

Actual Behavior

The length of tokenizer vocab size and the BERT's word embedding layer dimension is not the same

Steps to Reproduce the Problem

  1. Load the model: model = AutoModel.from_pretrained('indobenchmark/indobert-base-p1')
  2. Print the model: print(model)

image

  1. Load the tokenizer: tokenizer = AutoTokenizer.from_pretrained('indobenchmark/indobert-base-p1')
  2. Print the length of toikenizer: print(len(tokenizer))
    image
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@louisowen6
0