Compressed and Optimized Language Models with Bi-LSTM Architectures
- First clone this repository.
- Install required pip packages by issuing following command
pip install -r requirements.txt - Navigate to
configdirectory and open thePruneLM.cfgfile. - Provide the necessary information needed for the compression. (The details about how to provide relevant configs are listed in the
PruneLM.cfg) - Navigate back to the base directory.
- Start the compression by running the
main.pyfile.
- Download and install Prometheus from this URL. (**Note: Select the relevant OS type before downloading)
- Download and install Grafana from this url. (**Note: Select the relevant OS type before downloading)
- Run the prometheus server.
- Start the Grafana service and navigate to Grafana Home with
localhost:3000URL. - Then import the dashboards provided in the
statistics/dashboarddirectory.