Spaces:

open-llm-leaderboard

/

open_llm_leaderboard

like 11.8k

Running on CPU Upgrade

Do you have experience with model evaluation, especially with using lm-evaluation-harness to test models and compare with commercial foundation model results?
Minutes of your time to give us some guidance at the outset will almost certainly save us days/weeks of spinning wheels unnecessarily because we choose the wrong tools, scaffolding, metrics to focus on, etc.
Very eager to either just have a quick chat, or potentially to (paid) consulting if it seems like it's a fit and you have hours rather than minutes.
Thank you very much if you can help.