Evaluating on a new benchmark

[andimarafioti]

Hi guys 👋

We are working on a new long-video benchmark and would love to evaluate Long-VITA! We implemented our eval on a fork of lmms-eval, so we can evaluate any model present in the repo, but Long-VITA isn't there. Would you be willing to add it so that we can run the benchmark?
Thank you!

Andi from Hugging face

[shenyunhang]

Hi Andi,
Thanks for reaching out! We'd be happy to have Long-VITA included in your benchmark evaluation. Let us know how we can help with the integration.