SEBIS/code_trans_t5_small_program_synthese

The CodeTrans model is based on the t5-small model architecture . It has its own SentencePiece vocabulary model . It used single-task training on Program Synthesis dataset . It could be used to generate lisp inspired DSL code given the human language description tasks . The supervised training tasks datasets can be downloaded on Link. The code documentation tasks can be evaluated on different programming languages (in BLEU score): Different models achieves the following results on different languages . For the test results, different models achieve the . following results :. The test results are . the following . test results:. The results are. the result of the . test . of the code documentation . tasks,,