A fast inference library for running LLMs locally on modern consumer-class GPUs

Inference code for CodeLlama models

The simplest way to run LLaMA on your local machine

Inference code for Llama models

The RunBugRun dataset of executable bugs

This repository is to support contributions for tools for the Project CodeNet dataset hosted in DAX

CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)

Official code of our work, AVATAR: A Parallel Corpus for Java-Python Program Translation.

A simple tool for detecting near-duplicate source code

Reference implementation of code generation projects from Facebook AI Research. General toolkit to apply machine learning to code, from dataset creation to model training and evaluation. Comes with…

A Dataset of Python Challenges for AI Research

EvoSuite - automated generation of JUnit test suites for Java classes

A multi-lingual program repair benchmark set based on the Quixey Challenge

Public release of the TransCoder research project https://arxiv.org/pdf/2006.03511.pdf

A Python toolbox for performing gradient-free optimization