SEBIS/code_trans_t5_base_code_documentation_generation_php

The CodeTrans model is based on the t5-base model architecture . It can be used on unparsed and untokenized PHP code . The model could be used to generate the description for the PHP function or be fine-tuned on other PHP code tasks . It works best with tokenized PHP functions, but the performance should be better if the PHP code is tokenized . It has its own SentencePiece vocabulary model . The supervised training tasks datasets can be downloaded on Link .Evaluation results are based on different programming languages (in BLEU score): For the code documentation tasks, different models achieves the following results on different languages . For the test results, different,