SEBIS/code_trans_t5_small_source_code_summarization_csharp_multitask

The CodeTrans model is based on the t5-small 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 . The model could be used to generate the description for the csharp function or be fine-tuned on other csharp code tasks . It can be used on unparsed and untokenized csharp codes, but the performance should be better if the code is tokenized . The training procedure was trained on a single TPU Pod V3-8 for 300,000 steps in total, using sequence length 512 (batch size 4096). The optimizer,