Compressor: Compressing Pre-trained Models of Code into 3 MB
Compressor is an approach that can compress the pre-trained models of code into extremely small models with negligible performance sacrifice. Compressor proposes a genetic algorithm (GA)-based strategy to guide the simplification process.
Launch on Chameleon
Feedback
Launching this artifact will open it within Chameleon’s shared Jupyter experiment environment, which is accessible to all Chameleon users with an active allocation.
Download ArchiveDownload an archive containing the files of this artifact.
Download with git
Clone the git repository for this artifact, and checkout the version's commit
git clone https://github.com/yhfie/Compressor-CHI.git
# cd into the created directory
git checkout 90a371d8069a94258696941bd6119283b1799bd1
Submit feedback through GitHub issues