Skip to content

Add qwen3 family #1948

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

Merged
merged 27 commits into from
Jul 2, 2025
Merged

Add qwen3 family #1948

merged 27 commits into from
Jul 2, 2025

Conversation

tianyuan211
Copy link
Contributor

What does this PR do?

Fixes # (issue)

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you make sure to update the documentation with your changes?
  • Did you write any new necessary tests?

@regisss
Copy link
Collaborator

regisss commented Apr 24, 2025

On which version of Transformers is this PR based?

@tianyuan211
Copy link
Contributor Author

On which version of Transformers is this PR based?

this is for Transformers 4.51, which includes the qwen3 model; I just add the qwen3 code part, not changing the other code which may influence the generation process.

@regisss
Copy link
Collaborator

regisss commented Apr 30, 2025

@tianyuan211 Can you also add the following please?

  • a text-generation test here: https://github.com/huggingface/optimum-habana/blob/main/tests/test_text_generation_example.py
  • update this line in the README "Qwen2" --> "Qwen2 / Qwen3":
    | Qwen2 | <li>Single card</li> | <li>Single card</li> | <li>[language modeling](https://github.com/huggingface/optimum-habana/tree/main/examples/language-modeling)</li><li>[text generation](https://github.com/huggingface/optimum-habana/tree/main/examples/text-generation)</li> |
  • same in the table of the doc:
    | Qwen2 | <div style="text-align:left"><li>Single card</li></div> | <div style="text-align:left"><li>Single card</li></div> | <li>[language modeling](https://github.com/huggingface/optimum-habana/tree/main/examples/language-modeling)</li><li>[text generation](https://github.com/huggingface/optimum-habana/tree/main/examples/text-generation)</li> |

@tianyuan211 tianyuan211 reopened this May 8, 2025
@Wei-Lin-Intel Wei-Lin-Intel mentioned this pull request May 21, 2025
3 tasks
@tianyuan211 tianyuan211 changed the title Add qwen3 Add qwen3 family May 21, 2025
@emascarenhas
Copy link
Contributor

@tianyuan211 , Do you still need this PR?

@tianyuan0211
Copy link
Contributor

@tianyuan211 , Do you still need this PR?

Yes, I'm waiting for the transformers 4.51 update to merge, which is pr #1943 ,

Copy link

The code quality check failed, please run make style.

@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.

Copy link
Collaborator

@regisss regisss left a comment

Choose a reason for hiding this comment

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

LGTM

Copy link

github-actions bot commented Jul 1, 2025

The code quality check failed, please run make style.

@regisss
Copy link
Collaborator

regisss commented Jul 1, 2025

@tianyuan211 Please solve the issues raised by running make style

@tianyuan211
Copy link
Contributor Author

@tianyuan211 Please solve the issues raised by running make style

now it's ready

@regisss regisss merged commit ccddca2 into huggingface:main Jul 2, 2025
2 of 4 checks passed
regisss pushed a commit that referenced this pull request Jul 2, 2025
astachowiczhabana pushed a commit to HabanaAI/optimum-habana-fork that referenced this pull request Jul 3, 2025
astachowiczhabana added a commit that referenced this pull request Jul 4, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

6 participants