Code Trans T5 Base Api Generation Multitask Finetune

🚀 CodeTrans model for api recommendation generation

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

🚀 Quick Start

The CodeTrans model is designed for API recommendation generation. It uses the t5-base architecture and has been fine - tuned for Java API tasks.

✨ Features

• Based on the t5-base model with its own SentencePiece vocabulary model.
• Trained on 13 supervised tasks in software development and 7 unsupervised datasets using multi - task training.
• Fine - tuned for API recommendation generation for Java APIs.

📦 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_base_api_generation_multitask_finetune"),
    tokenizer=AutoTokenizer.from_pretrained("SEBIS/code_trans_t5_base_api_generation_multitask_finetune", 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-base 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. It is then fine - tuned on the api recommendation generation task for the java apis.

Intended Uses & Limitations

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

🔧 Technical Details

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 500,000 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.

Fine - tuning

This model was then fine - tuned on a single TPU Pod V2 - 8 for 320,000 steps in total, using sequence length 512 (batch size 256), using only the dataset only containing api recommendation generation data.

Evaluation Results

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

Created by Ahmed Elnaggar | LinkedIn and Wei Ding | LinkedIn