-10.5281%2Fzenodo.12737073-blue){kind=icon}
This benchmark is part of the JUPITER Benchmark Suite. See the repository of the suite for some general remarks.
This repository contains the MMoCLIP benchmark. DESCRIPTION.md contains details for compilation, execution, and evaluation. MMoCLIP runs OpenCLIP, an open source implementation of CLIP, which is a multi-modal contrastive model that can learn image and text representations from a dataset of image-text pairs.
The source code of OpenCLIP is included in the ./src/ subdirectory as a submodule from the upstream OpenCLIP repository at github.com/mlfoundations/open_clip.