SEBIS/code_trans_t5_large_code_documentation_generation_java_multitask

The CodeTrans model is based on the t5-large model architecture . It has its own SentencePiece vocabulary model . The model is trained on tokenized java code functions . It could be used to generate the description for the java function or be fine-tuned on other java code tasks . It can be used on unparsed and untokenized java codes, but if the java code is tokenized, the performance should be better . It was trained on a single TPU Pod V3-8 for 180,000 steps in total, using sequence length 512 (batch size 4096) It has a total of approximately 220M parameters and was trained using the encoder-dec,