Code Trans T5 Large Code Documentation Generation Python Multitask

🚀 CodeTrans model for code documentation generation python

A pre - trained model on the Python programming language using the T5 large model architecture, designed for generating code documentation.

This model is a pre - trained model for the Python programming language, leveraging the T5 large model architecture. It was first released in this repository. Trained on tokenized Python code functions, it performs best with such inputs.

✨ Features

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

📦 Installation

No 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 Python 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_python_multitask"),
    tokenizer=AutoTokenizer.from_pretrained("SEBIS/code_trans_t5_large_code_documentation_generation_python_multitask", skip_special_tokens=True),
    device=0
)

tokenized_code = "def e ( message , exit_code = None ) : print_log ( message , YELLOW , BOLD ) if exit_code is not None : sys . exit ( exit_code )"
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 Python function or be fine - tuned on other Python code tasks. It can be used on unparsed and untokenized Python code. However, if the Python 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 80,000 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