SEBIS/code_trans_t5_base_code_documentation_generation_java

The CodeTrans model is based on the t5-base model architecture . It has its own SentencePiece vocabulary model . It can be used on unparsed and untokenized java code . The model could be used to generate the description for the java function or be fine-tuned on other java code tasks . It works best with tokenized java functions . The code documentation task was created by Ahmed Elnaggar and Wei-Wein Ding . The training data can be downloaded on Link.this repository . For the code documentation tasks, different models achieves the following results on different programming languages (in BLEU score): The test results are based on various programming languages .,