EmbodiedAgentInterface/backend

Depending on whether you want to use lighteval or lm_eval for your evaluations, you might need to complete the requirements.txt file to contain relevant dependencies.

You'll also need to select, in app.py, whether you want to use the ligtheval or lm_eval by selecting the correct import and commenting the other.

All env variables that you should need to edit to launch the evaluations should be in envs.