Spaces:

open-llm-leaderboard

/

open_llm_leaderboard

like 10.1k

Running on CPU Upgrade

Hi everyone,

Trying to build my own private leaderboard for benchmarking! I've been checking out the Hugging Face demo leaderboard (https://huggingface.co/demo-leaderboard & https://huggingface.co/demo-leaderboard-backend) as a reference, but I'm curious if anyone has other resources they recommend.

Ideally, I'd like to benchmark my models with both common datasets and custom ones. Any insights or suggestions would be greatly appreciated!