Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
How to Build Similar Leaderboard for Non-text Domain Language Models?
#727
by
katarinayuan
- opened
Hi,
Thank you so this amazing benchmark. The formular of automatically evaluating LLMs by uploading them via HugginFace model card seems to be very user-friendly and attractive. Is there any way for developers to learn how to build similar benchmarks for other domain LMs? For example, would the source code for this leaderboard be open available?
Hi,
The easiest for this would be to follow the documentation for the leaderboards on the hub, here!
It will point you to templates, docs, and everything you need to build your own leaderboard :)
clefourrier
changed discussion status to
closed