CodeT5 (large-size model pretrained with NTP objective on Python)
Model description
CodeT5 is a family of encoder-decoder language models for code from the paper: CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation by Yue Wang, Weishi Wang, Shafiq Joty, and Steven C.H. Hoi.
The checkpoint included in this repository is denoted as CodeT5-large-ntp-py (770M), which is introduced by the paper: CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning by Hung Le, Yue Wang, Akhilesh Deepak Gotmare, Silvio Savarese, Steven C.H. Hoi.
Training data
CodeT5-large-ntp-py was pretrained on CodeSearchNet data in six programming languages (Ruby/JavaScript/Go/Python/Java/PHP) and GCPY (the Python split of Github Code) data. See Section 4.1 of the paper for more details.
Training procedure
CodeT5-large-ntp-py was first pretrained using Masked Span Prediction (MSP) objective on CodeSearchNet for 150 epochs and on GCPY for 10 epochs, followed by another 10 epochs on GCPY using Next Token Prediction (NTP) objective. See Section 4.1 of the paper for more details.
Evaluation results
We evaluated this checkpoint on APPS benchmark. See Table 5 of the paper for more details.
How to use
This model can be easily loaded using the T5ForConditionalGeneration functionality:
from transformers import AutoTokenizer, T5ForConditionalGeneration
tokenizer = AutoTokenizer.from_pretrained("Salesforce/codet5-large-ntp-py")
model = T5ForConditionalGeneration.from_pretrained("Salesforce/codet5-large-ntp-py")
text = "def hello_world():"
input_ids = tokenizer(text, return_tensors="pt").input_ids
# simply generate a single sequence
generated_ids = model.generate(input_ids, max_length=128)
print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
Ethical Considerations
This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly impact people’s lives, rights, or safety. For further guidance on use cases, refer to our AUP and AI AUP.
BibTeX entry and citation info
@inproceedings{CodeT52021,
author = {Yue Wang and Weishi Wang and Shafiq R. Joty and Steven C. H. Hoi},
title = {CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation},
booktitle = {EMNLP},
pages = {8696--8708},
publisher = {Association for Computational Linguistics},
year = {2021}
}
@article{CodeRL2022
author = {Hung Le, Yue Wang, Akhilesh Deepak Gotmare, Silvio Savarese, Steven C.H. Hoi},
title = {CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning},
journal = {arXiv preprint},
volume = {abs/2207.01780},
year = {2022}
}