đ CodeTrans model for api recommendation generation
A pre - trained model for API recommendation generation using the T5 small model architecture, which can assist in Java programming tasks.
đ Quick Start
This is a pre - trained model for API recommendation generation, leveraging the T5 small model architecture. It was initially released in this repository.
⨠Features
- Based on the
t5 - small
model with its own SentencePiece vocabulary model.
- Trained on 13 supervised tasks in software development and 7 unsupervised datasets through multi - task training.
- Fine - tuned for API recommendation generation for Java APIs.
đĻ Installation
No specific installation steps are provided in the original document.
đģ Usage Examples
Basic Usage
Here's how to use this model to generate Java function documentation using the Transformers SummarizationPipeline:
from transformers import AutoTokenizer, AutoModelWithLMHead, SummarizationPipeline
pipeline = SummarizationPipeline(
model=AutoModelWithLMHead.from_pretrained("SEBIS/code_trans_t5_small_api_generation_multitask_finetune"),
tokenizer=AutoTokenizer.from_pretrained("SEBIS/code_trans_t5_small_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.
đ Documentation
Model Description
This CodeTrans model is based on the t5 - small
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.
đ§ 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 1,150,000 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 achieve the following results on different programming languages (in BLEU score):
Test results :
Property |
Details |
Model Type |
CodeTrans model for API recommendation generation |
Training Data |
The supervised training tasks datasets can be downloaded on Link |
Language / Model |
Java |
CodeTrans - ST - Small |
68.71 |
CodeTrans - ST - Base |
70.45 |
CodeTrans - TF - Small |
68.90 |
CodeTrans - TF - Base |
72.11 |
CodeTrans - TF - Large |
73.26 |
CodeTrans - MT - Small |
58.43 |
CodeTrans - MT - Base |
67.97 |
CodeTrans - MT - Large |
72.29 |
CodeTrans - MT - TF - Small |
69.29 |
CodeTrans - MT - TF - Base |
72.89 |
CodeTrans - MT - TF - Large |
73.39 |
State of the art |
54.42 |
Created by Ahmed Elnaggar | LinkedIn and Wei Ding | LinkedIn