SEBIS/code_trans_t5_base_code_comment_generation_java_multitask_finetune

CodeTrans model is based on the t5-base model architecture . It has its own SentencePiece vocabulary model . It used multi-task training on 13 supervised tasks in the software development domain and 7 unsupervised datasets . It is then fine-tuned on the code comment generation task for the java function/method . This model is trained on tokenized java code functions . It could be used to generate the description for a java function . It can be used on unparsed and untokenized java codes, however, the performance should be better if the java code is tokenized . The optimizer used is AdaFactor with inverse square root learning rate schedule for pre-training,