claudios/plbart-c-cpp-defect-detection

This is an unofficial reupload of uclanlp/plbart-c-cpp-defect-detection in the SafeTensors format using transformers 4.40.1. The goal of this reupload is to prevent older models that are still relevant baselines from becoming stale as a result of changes in HuggingFace. Additionally, I may include minor corrections, such as model max length configuration.

Please see the original repo for more information.

Original model card below:

PLBART is a Transformer model

• —PLBART is a sequence-to-sequence model pre-trained on a large collection Java and Python functions and natural language descriptions collected from Github and StackOverflow, respectively.
• —PLBART is pre-trained via denoising autoencoding (DAE) and uses three noising strategies: token masking, token deletion, and token infilling (shown below in the three examples).

<div align="center">

<table> <thead> <tr> <th>Noisy Input</th> <th>Original Sequence</th> </tr> </thead> <tbody> <tr> <td>Is 0 the <strong>[MASK]</strong> Fibonacci <strong>[MASK]</strong> ? <em>&lt;En&gt;</em></td> <td><em>&lt;En&gt;</em> Is 0 the <strong>first</strong> Fibonacci <strong>number</strong> ?</td> </tr> <tr> <td>public static main ( String args [ ] ) { date = Date ( ) ; System . out . ( String . format ( " Current Date : % tc " , ) ) ; } <em>&lt;java&gt;</em></td> <td><em>&lt;java&gt;</em> public static <strong>void</strong> main ( String args [ ] ) { <strong>Date</strong> date = new Date ( ) ; System . out . <strong>printf</strong> ( String . format ( " Current Date : % tc " , <strong>date</strong> ) ) ; }</td> </tr> <tr> <td>def addThreeNumbers ( x , y , z ) : NEWLINE INDENT return <strong>[MASK]</strong> <em>&lt;python&gt;</em></td> <td><em>&lt;python&gt;</em> def addThreeNumbers ( x , y , z ) : NEWLINE INDENT return <strong>x + y + z</strong></td> </tr> </tbody> </table>

</div>