Research works upon pre-trained code language models and prompt tuning
- initialize python env
conda create -n codelm python=3.8 pip install torch --extra-index-url https://download.pytorch.org/whl/cu113 pip install -r requirements.txt
- link data folder
ln -s ~/Data/CodeLM-Prompt data sudo chmod 777 -R data
Evaluating the performances of the pre-trained LMs for generating explanations for variables