Spaces:

HuggingFaceH4

/

open_llm_leaderboard

like 9.63k

Running on CPU Upgrade

There is so much more; I think people may help. I am considering writing a script to:

• Retrieve all model cards:
  • Flag it if it uses the "metamathqa" dataset.
  • Flag it if it includes the word "metamath" with a pattern.

Following the creation of this PR, an ephemeral Space HuggingFaceH4/open_llm_leaderboard-ci-pr-478 has been started. Any changes pushed to this PR will be synced with the test Space.
Since this PR has been created by a trusted author, the ephemeral Space has been configured with the correct hardware, storage, and secrets.
(This is an automated message.)

Lot of models use Marcoroni and Metamath-Cyberton-Starling as base model btw.

It's working well @SaylorTwift , good job, merging your PR

PR is now merged/closed. The ephemeral Space has been deleted.
(This is an automated message.)