Tanay Mehta

Native support for PIL Images in Lance

1

Add the native support for PIL images in Lance instead of storing images in Bytes format.

Hi, I was wondering if there is a way supported by Python API to run multiple eval benchmarks on multiple models (by passing in a list of models and their...

Hi, there's a bug in the [`visualize-wandb.ipynb`](https://github.com/EleutherAI/lm-evaluation-harness/blob/main/examples/visualize-wandb.ipynb): In the example notebook's final cell, the `tasks` are comma-separated in a single string. However running that on a fresh install of `lm_eval`...