code_trans_t5_large_program_synthese_transfer_learning_finetune

CodeTrans model for program synthesis

Pretrained model on programming language lisp inspired DSL using the t5 large model architecture. It was first released in this repository.

Model description

This CodeTrans model is based on the t5-large model. It has its own SentencePiece vocabulary model. It used transfer-learning pre-training on 7 unsupervised datasets in the software development domain. It is then fine-tuned on the program synthesis task for the lisp inspired DSL code.

Intended uses & limitations

The model could be used to generate lisp inspired DSL code given the human language description tasks.

How to use

Here is how to use this model to generate lisp inspired DSL code using Transformers SummarizationPipeline:

from transformers import AutoTokenizer, AutoModelWithLMHead, SummarizationPipeline

pipeline = SummarizationPipeline(
    model=AutoModelWithLMHead.from_pretrained("SEBIS/code_trans_t5_large_program_synthese_transfer_learning_finetune"),
    tokenizer=AutoTokenizer.from_pretrained("SEBIS/code_trans_t5_large_program_synthese_transfer_learning_finetune", skip_special_tokens=True),
    device=0
)

tokenized_code = "you are given an array of numbers a and a number b , compute the difference of elements in a and b"
pipeline([tokenized_code])

Run this example in colab notebook.

Training data

The supervised training tasks datasets can be downloaded on Link

Training procedure

Transfer-learning Pretraining

The model was trained on a single TPU Pod V3-8 for 240,000 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 3,500 steps in total, using sequence length 512 (batch size 256), using only the dataset only containing lisp inspired DSL data.

Evaluation results

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

Test results :

Created by Ahmed Elnaggar | LinkedIn and Wei Ding | LinkedIn