SEBIS/code_trans_t5_large_api_generation_multitask

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 . The model could be used to generate API usage for the java programming tasks . It was first released in this repository in September 2013 . The code documentation test results are based on different programming languages (in BLEU score) For example, the code documentation task was run by Transformers SummarizationPipeline using the model to generate java function documentation using a single TPU Pod V3-8 for 240,000 steps in total, using sequence length 512,