SEBIS/code_trans_t5_base_code_documentation_generation_python

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 python code . The model could be used to generate the description for the python function or be fine-tuned on other python code tasks . It works best with tokenized python functions, but the performance should be better if the python code is tokenized . The code documentation task was created by Ahmed Elngar and Wei-Weinang Wei-Dong Wei on the CodeSearchNet Corpus python dataset . It used single-task training on CodeSearch Net Corpus python datasets . The supervised training tasks datasets,