metadata

language: code
datasets:
  - code_search_net

CoText (1-CC)

Introduction

Paper: CoTexT: Multi-task Learning with Code-Text Transformer

Authors: Long Phan, Hieu Tran, Daniel Le, Hieu Nguyen, James Anibal, Alec Peltekian, Yanfang Ye

How to use

Supported languages:

"go"
"java"
"javascript"
"php"
"python"
"ruby"

For more details, do check out our Github repo.

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("razent/cotext-1-cc")  
model = AutoModelForSeq2SeqLM.from_pretrained("razent/cotext-1-cc")

sentence = "def add(a, b): return a + b"
text =  "python: " + sentence + " </s>"

encoding = tokenizer.encode_plus(text, pad_to_max_length=True, return_tensors="pt")
input_ids, attention_masks = encoding["input_ids"].to("cuda"), encoding["attention_mask"].to("cuda")

outputs = model.generate(
    input_ids=input_ids, attention_mask=attention_masks,
    max_length=256,
    early_stopping=True
)

for output in outputs:
    line = tokenizer.decode(output, skip_special_tokens=True, clean_up_tokenization_spaces=True)
    print(line)

Citation

@misc{https://doi.org/10.48550/arxiv.2105.08645,
  doi = {10.48550/ARXIV.2105.08645},
  url = {https://arxiv.org/abs/2105.08645},
  author = {Phan, Long and Tran, Hieu and Le, Daniel and Nguyen, Hieu and Anibal, James and Peltekian, Alec and Ye, Yanfang},
  title = {CoTexT: Multi-task Learning with Code-Text Transformer},
  publisher = {arXiv},
  year = {2021},
  copyright = {Creative Commons Attribution 4.0 International}
}