git clone git@github.com:asappresearch/workflow-response.git
cd workflow-response
pyenv virtualenv workflow-response
pyenv activate workflow-response
Install the required packages:
pip install -r requirements.txt
Download and create datasets for training.
for dataset in abcd multi_woz; do
bash scripts/dataproc/download_process_${dataset}.sh
done
bash bash/gpt2_train.sh
bash bash/bert_reward/train.sh
bash bash/quark_run.sh
Evaluate RL model:
python eval/interactive_quark_eval.py
Human evaluations:
python eval/process_human_eval.py