SEBIS/code_trans_t5_base_program_synthese_transfer_learning_finetune

The CodeTrans model is based on the t5-base model . It used transfer-learning pre-training on 7 unsupervised datasets in the software development domain . 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 code documentation tasks can be downloaded on Link.com/CodeTrans-ST-Small or Link . It,