Code Trans T5 Large Code Documentation Generation Java Multitask

🚀 CodeTrans Model for Java Code Documentation Generation

This is a pre - trained model for the Java programming language, leveraging the T5 large model architecture. It was initially released in this repository. This model is trained on tokenized Java code functions and performs optimally with such tokenized functions.

✨ Features

• Based on the t5 - large model with its own SentencePiece vocabulary model.
• Utilized multi - task training on 13 supervised tasks in the software development domain and 7 unsupervised datasets.
• Can generate descriptions for Java functions or be fine - tuned for other Java code tasks.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

Here is how to use this model to generate Java function documentation using Transformers SummarizationPipeline:

from transformers import AutoTokenizer, AutoModelWithLMHead, SummarizationPipeline

pipeline = SummarizationPipeline(
    model=AutoModelWithLMHead.from_pretrained("SEBIS/code_trans_t5_large_code_documentation_generation_java_multitask"),
    tokenizer=AutoTokenizer.from_pretrained("SEBIS/code_trans_t5_large_code_documentation_generation_java_multitask", skip_special_tokens=True),
    device=0
)

tokenized_code = "public static < T , U > Function < T , U > castFunction  ( Class < U > target ) { return new CastToClass < T , U > ( target ) ; }"
pipeline([tokenized_code])

Run this example in colab notebook.

📚 Documentation

Model Description

This CodeTrans model is based on the t5 - large model. 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.

Intended Uses & Limitations

The model 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 code. However, if the Java code is tokenized, the performance should be better.

Training Data

The supervised training tasks datasets can be downloaded on Link

Training Procedure

Multi - task Pretraining

The model 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 - decoder architecture. The optimizer used is AdaFactor with inverse square root learning rate schedule for pre - training.

Evaluation Results

For the code documentation tasks, different models achieve the following results on different programming languages (in BLEU score):

Test results :

Created by Ahmed Elnaggar | LinkedIn and Wei Ding | LinkedIn