Evaluation Module Request : A standard way to evaluate the fine-tuned model

Hey, I just finished my toy project on fine-tuning the ColBertV2 model and I am wondering if there are or will be any standard evaluation datasets and methods wrapped in the package so that we can easily evaluate the fine-tuned model. Thanks!

No files, tests, or entry points are identified in the issue. Start by reviewing the package's existing fine-tuning and evaluation capabilities, then define which standard datasets and evaluation methods should be supported and what a completed evaluation workflow would produce.

Written by the indexing model from the issue text.