Fabien Ric

Hi there, I'm able to run Tensorflow Serving on my M1 by using this custom build: https://github.com/emacski/tensorflow-serving-arm `docker pull emacski/tensorflow-serving:latest-linux_arm64` `docker run -t --rm -p 8501:8501 --mount type=bind,source=/tmp/model_name/,target=/models/model_name/ -e MODEL_NAME=model_name...

It would be nice as well to be able to filter a tasks or list of tasks to only run generate_until evaluations, when using the lm_eval command line, for example...