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

Support for Falcon2-11B #30771

Merged
merged 14 commits into from
May 13, 2024
Merged

Conversation

Nilabhra
Copy link
Contributor

This PR adds support for the Falcon2-11B architecture.

@amyeroberts
Copy link
Collaborator

cc @ArthurZucker

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.

LGTM, let's make the test go green and good to go!
For outside readers, this does not go against the philosophy as the falcon modeling code is already not very much in accordance to our philosophy 😉 (it has a lot of code paths etc).
Not super happy but it's the best compromise for this model

@@ -602,6 +602,25 @@ def test_lm_generate_falcon(self):

self.assertEqual(output_str, EXPECTED_OUTPUT)

@slow
@require_bitsandbytes
def test_lm_generate_falcon_11b(self):
Copy link
Collaborator

Choose a reason for hiding this comment

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

thanks for adding a test!

@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.

@Nilabhra
Copy link
Contributor Author

@ArthurZucker The tests have passed.

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.

🔥

@ArthurZucker ArthurZucker merged commit e52741f into huggingface:main May 13, 2024
21 checks passed
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.

None yet

5 participants