Does pixmo-points-eval have support in the evaluation scripts?

Hello, thanks for releasing this dataset and code!

I noticed that in [molmo/launch_scripts/eval_downstream.py](https://github.com/allenai/molmo/blob/main/launch_scripts/eval_downstream.py)
, there doesn’t seem to be an entry for the pixmo-points-eval task.

Is pixmo-points-eval currently supported by the evaluation pipeline?

If not, what’s the recommended way to run evaluation on this dataset?

Are there any example commands or configs available to reproduce results with this benchmark?

Thanks a lot for clarifying!