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 Storm-7B, Storm-7B (best-of-64) to AlpacaEval #344

Merged
merged 4 commits into from
Jun 21, 2024

Conversation

yifan123
Copy link
Contributor

We have updated the results of our Storm-7B model, achieving a higher LC Win rate. In addition, we replaced the beam search results with those from the best-of-n approach, yielding more promising outcomes.

You can find our technical report at https://arxiv.org/pdf/2406.11817 and access our model at https://huggingface.co/jieliu/Storm-7B. Thank you for reviewing our pull request and for your valuable feedback.

@YannDubs
Copy link
Collaborator

Great work @yifan123 !

I can’t merge this PR rn because I want to remove the purest issue before. I will do that ASAP but I may not have time to do that before end of next week

@yifan123
Copy link
Contributor Author

Dear YannDubs,

I’m not quite sure what "the purest issue" refers to. Could you kindly clarify it and let me know if any modifications are needed for our PR? Thank you!

Best,

Jie Liu

@YannDubs
Copy link
Collaborator

Sorry I meant "pytest issue" in the CI. Anyways it's done now: congrats!

@YannDubs YannDubs merged commit 58acae6 into tatsu-lab:main Jun 21, 2024
2 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.

2 participants