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.

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

Embeddings from BERT for original tokens #148

Closed
nihalnayak opened this issue Dec 27, 2018 · 1 comment
Closed

Embeddings from BERT for original tokens #148

nihalnayak opened this issue Dec 27, 2018 · 1 comment

Comments

@nihalnayak
Copy link

nihalnayak commented Dec 27, 2018 •
edited
Loading

I am trying out the extract_features.py example program. I noticed that a sentence gets split into tokens and the embeddings are generated. For example, if you had the sentence “Definitely not”, and the corresponding workpieces can be [“Def”, “##in”, “##ite”, “##ly”, “not”]. It then generates the embeddings for these tokens.

My question is how do I train an NER system on CoNLL dataset?

I want to extract embeddings for original tokens for training an NER with a neural architecture. If you have come across any resource that gives a clear explanation on how to carry this out, post it here.
@thomwolf
Copy link
Member

Hi, you should read the discussion in #64. I left this issue open for reference on these questions.
Don't hesitate to participate there.

ocavue pushed a commit to ocavue/transformers that referenced this issue Sep 13, 2023
@xenova
Add support for computing CLIP image and text embeddings separately (C…
2fde656 
…loses huggingface#148) (huggingface#227)

* Define custom CLIP ONNX configs

* Update conversion script

* Support specifying custom model file name

* Use int64 for CLIP input ids

* Add support for CLIP text and vision models

* Fix JSDoc

* Add docs for `CLIPTextModelWithProjection`

* Add docs for `CLIPVisionModelWithProjection`

* Add unit test for CLIP text models

* Add unit test for CLIP vision models

* Set resize precision to 3 decimal places

* Fix `RawImage.save()` function

* Throw error when reading image and status != 200

* Create basic semantic image search application

* Separate out components

* Add `update-database` script

* Update transformers.js version
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
2 participants
@nihalnayak @thomwolf