​ python >= 3.7

​ pytorch == 1.12.1

​ Transformers >= 3.3.0

​ 1. We use MDRDC dataset for training and testing. And we rename the path as '../MDRDC_DATASET'.

​ 2. Please download pretrain model bert and gpt2.

3.Replace the bert_model_path and gpt2_model_path in config_n.py

​ 4.run in command line

	sbatch preprocess.sh

	sbatch pretrain.sh

	sbatch train.sh

You can modify the config_n.py for parameter modification or in command line by add argument.

	sbatch tdgpn.sh

	sbatch toxicbuddy.sh