Márton Kardos
Márton Kardos
I'm using this branch and PR to add the necessary changes to the library for a leaderboard. So far, I have renamed `MTEBResults` to `TaskResult` and added a `BenchmarkResults` object...
Currently, many of the fields in model metadata are not filled. These should either be specified manually or we should find ways to derive them (from HuggingFace Hub for example.)
Since we would like to release the leaderboard as soon as possible (especially since the paper got accepted for ICLR), I would love to open a discussion about what we...