SEBIS/code_trans_t5_base_program_synthese_multitask_finetune

The CodeTrans model is based on the t5-base model . It used multi-task training on 13 supervised tasks in the software development domain and 7 unsupervised datasets . It is then fine-tuned on the program synthesis task for the lisp inspired DSL code . It has a total of approximately 220M parameters and was trained using the encoder-decoder architecture . The model was trained on a single TPU Pod V3-8 for 500,000 steps in total, using sequence length 512 (batch size 256) It has its own SentencePiece vocabulary model. The model could be used to generate lisp-inspired DSL code given the human language description tasks .,