Guide to using pre-trained large language models of source code

Home of CodeT5: Open Code LLMs for Code Understanding and Generation

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

Code for "Typilus: Neural Type Hints" PLDI 2020

A static analysis library for computing graph representations of Python programs suitable for use with graph neural networks.

ManyTypes4Py: A benchmark Python dataset for machine learning-based type inference

Type4Py: Deep Similarity Learning-Based Type Inference for Python

A Graph-based Program Representation for Data Flow Analysis and Compiler Optimizations

Data and Code for Reproducing "Global Relational Models of Source Code"

A GitHub Action for suggesting Python type annotations.

Neural Variable Renaming for Decompiled Binaries

DeepBugs is a framework for learning bug detectors from an existing code corpus.

RosettaCode Data Project

DeepCS: Deep Code Search

Mining tool and large-scale datasets of single statement bug fixes in Python

PLUR (Programming-Language Understanding and Repair) is a collection of source code datasets suitable for graph-based machine learning. We provide scripts for downloading, processing, and loading t…

CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.

Generative model for code infilling and synthesis

Implementation of the paper "Language-agnostic representation learning of source code from structure and context".

This repository contains all the code for collecting large scale amounts of code from GitHub.

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

CodeBERTScore: an automatic metric for code generation, based on BERTScore

A framework for the evaluation of autoregressive code generation language models.

Data and code for "DocPrompting: Generating Code by Retrieving the Docs" @ICLR 2023

Reliable project licenses detector.

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 multi-programming language benchmark for LLMs

Self-hosted AI coding assistant

⚙️ A tool to build bug-fix benchmarks with GitHub Actions ⚙️