SEBIS/code_trans_t5_small_code_documentation_generation_ruby_multitask

The CodeTrans model is based on the t5-small model architecture . It has its own SentencePiece vocabulary model . The model is trained on tokenized ruby code functions . It could be used to generate the description for the ruby function or be fine-tuned on other ruby code tasks . It can be used on unparsed and untokenized ruby codes, but the performance should be better if the ruby code is tokenized . For example, this is how to use this model to generate ruby function documentation using Transformers SummarizationPipeline . It was trained using the encoder-decoder architecture and the optimizer used is AdaFactor with inverse square root learning rate,