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

Starcoder2 model - bis #29215

Merged
merged 26 commits into from
Feb 28, 2024
Merged

Starcoder2 model - bis #29215

merged 26 commits into from
Feb 28, 2024

Conversation

RaymondLi0
Copy link
Contributor

@RaymondLi0 RaymondLi0 commented Feb 22, 2024

The Starcoder2 model, adapted from Mistral. All changes are done through options, so Mistral itself is still supported.
Main changes:

  • Use layer norm
  • Use standard MLP
  • Add biases (optional)
  • Change (default?) tokenizer class
    *Embedding and residual dropout

It does not support absolute embeddings, so can't support Santacoder or Starcoder

Starcoder2-3B model: https://huggingface.co/bigcode/starcoder2-3b

Todo:

@younesbelkada @ArthurZucker @jlamypoirier

@RaymondLi0 RaymondLi0 mentioned this pull request Feb 22, 2024
@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

younesbelkada and others added 12 commits February 23, 2024 02:52
Copy link
Collaborator

@ArthurZucker ArthurZucker left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In #29228 I mention that static cache is not a blocker for the PR 😉

Copy link
Contributor

@younesbelkada younesbelkada left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks ! LGTM once we add the docs !

Copy link
Collaborator

@ArthurZucker ArthurZucker left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Let's go!

Comment on lines +21 to +23
Starcoder2 has been released with the paper [Stacoder-2](https://drive.google.com/file/d/17iGn3c-sYNiLyRSY-A85QOzgzGnGiVI3/view) by BigCode team.

Documentation page about the model is coming soon
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this is fairly short. Let's add that the main difference with mistral is dropout, as the authors would be nice to explain how much this influenced training for example.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yeah makes sense, I will take care of that after the official release

@younesbelkada younesbelkada merged commit 63caa37 into huggingface:main Feb 28, 2024
23 checks passed
@ArthurZucker
Copy link
Collaborator

Thank you for the PR @RaymondLi0. cc @loubnabnl and @lvwerra, next time let's make sure doc and paper links are fully completed before we merge, we require this for every model / organisation regardless of the release date 😉 let's make this an exception

@younesbelkada younesbelkada mentioned this pull request Mar 13, 2024
4 tasks
itazap pushed a commit that referenced this pull request May 14, 2024
* Copy model

* changes

* misc

* fixes

* add embed and residual dropout (#30)

* misc

* remove rms norm and gated MLP

* remove copied mentions where its not a copy anymore

* remove unused _shape

* copied from mistral instead

* fix copies

* fix copies

* add not doctested

* fix

* fix copyright

* Update docs/source/en/model_doc/starcoder2.md

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* Update src/transformers/models/starcoder2/configuration_starcoder2.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* Update src/transformers/models/starcoder2/configuration_starcoder2.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* fix doc

* revert some changes

* add fa2 tests

* fix styling nit

* fix

* push dummy docs

---------

Co-authored-by: Joel Lamy-Poirier <joel.lamy-poirier@servicenow.com>
Co-authored-by: younesbelkada <younesbelkada@gmail.com>
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
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

Successfully merging this pull request may close these issues.

5 participants