Giter Club home page Giter Club logo

repairllama's Introduction

RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair

If you use RepairLLaMA in academic research, please cite "RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair", Technical report, arXiv 2312.15698, 2023.

@techreport{repairllama2023,
  title={RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair},
  author={Silva, Andr{\'e} and Fang, Sen and Monperrus, Martin},
  url = {http://arxiv.org/abs/2312.15698},
  number = {2312.15698},
  institution = {arXiv},
}

This repository contains the code, model, and results to replicate the paper "RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair"

It is structured as follows:

  • repair-lora contains the RepairLLaMA low-rank adaptation of CodeLLaMA-7B, called "repair adapter"
  • results contains all generated patches for Defects4J and HumanEval-Java by all models (incl. full fine-tuning, lora, and code representations)
  • src contains the training and inference scripts
  • example contains an example notebook explaining how to load and prompt the RepairLLaMA model

Models

All fine-tuned models will soon be made available on HuggingFace

Datasets

The processed fine-tuning datasets are made available on HuggingFace at https://huggingface.co/datasets/ASSERT-KTH/repairllama-datasets. It contains the datasets used for training the RepairLLaMA models, one subset per input/output representation pair. To get the 30k..50k datasets we did further filtering based on the token length of input + output pairs being less than 1024 tokens.

If it interests you, you can also find these on our HuggingFace org:

Benchmarks

The evaluation benchmarks are Defects4J v2 and HumanEval-Java.

We focus on single-function bugs (i.e. bugs whose developer patch exclusively changes one function):

Note that the original HumanEval-Java contains a duplicate bug.

repairllama's People

Contributors

andre15silva avatar tomasandersonfang avatar kiki1643 avatar monperrus avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.