Code Trans T5 Small Api Generation

🚀 CodeTrans model for api recommendation generation

A pre - trained model for API recommendation generation using the T5 small model architecture, initially released in this repository.

🚀 Quick Start

The CodeTrans model is a pre - trained solution for API recommendation generation. It's based on the t5 - small architecture and can be used to generate API usage for Java programming tasks.

✨ Features

• Based on the t5 - small model architecture.
• Has its own SentencePiece vocabulary model.
• Trained on the Api Recommendation Generation dataset using single - task training.

📦 Installation

No specific installation steps are provided in the original README.

💻 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_small_api_generation"),
    tokenizer=AutoTokenizer.from_pretrained("SEBIS/code_trans_t5_small_api_generation", skip_special_tokens=True),
    device=0
)

tokenized_code = "parse the uses licence node of this package , if any , and returns the license definition if theres"
pipeline([tokenized_code])

Run this example in colab notebook.

📚 Documentation

Model description

This CodeTrans model is based on the t5 - small model. It has its own SentencePiece vocabulary model. It used single - task training on Api Recommendation Generation dataset.

Intended uses & limitations

The model could be used to generate api usage for the java programming tasks.

Training data

The supervised training tasks datasets can be downloaded on Link

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