SEBIS/code_trans_t5_base_api_generation_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 api recommendation generation task for the java apis. The model could be used to generate API usage for the . java programming tasks. It has its own SentencePiece vocabulary model. It is also able to generate java function documentation using Transformers SummarizationPipeline . The model was trained on a single TPU Pod V3-8 for 1,400,000 steps in total, using sequence length 512 (batch size 256). It has a total of approximately 220M,