SEBIS/code_trans_t5_base_program_synthese

The CodeTrans model is based on the t5-base model architecture . It has its own SentencePiece vocabulary model . It used single-task training on Program Synthesis dataset . The model could be used to generate lisp inspired DSL code based on human language description tasks . It was first released in this repository . The code documentation tasks can be downloaded on Link . For the code documentation task, different models achieves the following results on different programming languages (in BLEU score): test results : test results: test results on various programming languages . For example, the CodeTrans-ST-Small test results are: test result: test score: codeTrans-MT-Small, test,