SEBIS/code_trans_t5_large_source_code_summarization_csharp_multitask_finetune

The CodeTrans model is based on the t5-large 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 source code summarization task for the csharp code snippets . The model could be used to generate the description for a csharp function . It works best with tokenized csharp functions . It can be used on unparsed and untokenized code, but the performance should be better . It was trained on a single TPU Pod V3-8 for 260,000 steps in total, using sequence length,