SEBIS/code_trans_t5_small_api_generation_multitask_finetune

The CodeTrans model is based on the t5-small model architecture . It has its own SentencePiece vocabulary 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 api recommendation generation task for the java apis. The model could be used to generate API usage for the . java programming tasks . 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 a total of approximately 220M parameters and was trained using the encoder-decoder architecture. The optimizer used,