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

Add Yi Handler #543

Merged
merged 15 commits into from
Jul 26, 2024
Merged

Add Yi Handler #543

merged 15 commits into from
Jul 26, 2024

Conversation

fantasist
Copy link
Contributor

@fantasist fantasist commented Jul 22, 2024

Yi series models are authored by 01.ai. yi-large is known to be one of the SOTA LLMs. This PR adds a model handler for evaluating the public available endpoint of yi-large-fc, which is the version of yi-large model specialized in function calling capabilities.

@fantasist fantasist marked this pull request as ready for review July 22, 2024 22:41
Copy link

@luojy95 luojy95 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
Collaborator

@HuanzhiMao HuanzhiMao left a comment

Choose a reason for hiding this comment

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

Hey @fantasist,

Thank you for the PR.

In the decode_ast function, these lines should be removed. This will result in double-casting issue, and introduce false positives in evaluation score. For a detailed explanation, please check out #516. We addressed this issue for all model handlers there.

The rest of the PR looks great. Excited to see the yi-large-fc model on the leaderboard!

Copy link
Collaborator

@HuanzhiMao HuanzhiMao 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
Owner

@ShishirPatil ShishirPatil left a comment

Choose a reason for hiding this comment

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

Thanks for the PR. Can you please fill in the PR description as well! Post which we are happy to merge :)

@fantasist
Copy link
Contributor Author

Thanks for the PR. Can you please fill in the PR description as well! Post which we are happy to merge :)

Done!

Copy link
Owner

@ShishirPatil ShishirPatil left a comment

Choose a reason for hiding this comment

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

Thanks for the PR @fantasist and the reviews @luojy95! Appreciate your contributions to BFCL and the open-source community!

@ShishirPatil ShishirPatil merged commit 56f2cb2 into ShishirPatil:main Jul 26, 2024
@fantasist fantasist deleted the yi-fc branch July 26, 2024 05:03
ShishirPatil pushed a commit that referenced this pull request Jul 28, 2024
…ew Model) (#558)

This PR updates the leaderboard to reflect the addition of the following
models from SalesForce, Yi, and NousResearch.

- #532
- #543
- #556 
- #542

The scores for all the existing models are unchanged.
aw632 pushed a commit to vinaybagade/gorilla that referenced this pull request Aug 22, 2024
Yi series models are authored by 01.ai. `yi-large` is known to be one of
the SOTA LLMs. This PR adds a model handler for evaluating the public
available endpoint of `yi-large-fc`, which is the version of `yi-large`
model specialized in function calling capabilities.

---------

Co-authored-by: Yunfan Zhong <alanwake@in.ai>
Co-authored-by: Hector Lopez <hectorlopeze@in.ai>
Co-authored-by: Huanzhi Mao <huanzhimao@gmail.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.

4 participants