Stars
Data and evaluation scripts for "CodePlan: Repository-level Coding using LLMs and Planning", FSE 2024
Code and Data artifact for NeurIPS 2023 paper - "Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context". `multispy` is a lsp client library in Python intended to be used to…
AI4Code syntax repair tutorial for IAP 2023
Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)
📕machine learning tech collections at Microsoft and subsidiaries.
A concise but complete full-attention transformer with a set of promising experimental features from various papers
A pure-functional implementation of a machine learning transformer model in Python/JAX
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
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…
Repro is a library for easily running code from published papers via Docker.
Dynamic analysis framework for JavaScript
Thousands of code solutions with clear explanation @ onelinerhub.com
Parse, inspect, transform, and serialize content with syntax trees
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…
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Semantic parsers based on encoder-decoder framework
Codebase for testing whether hidden states of neural networks encode discrete structures.
A LLVM-based static analysis framework.
Spoon is a metaprogramming library to analyze and transform Java source code. 🥄 is made with ❤️, 🍻 and ✨. It parses source files to build a well-designed AST with powerful analysis and transformati…
📐 Compute distance between sequences. 30+ algorithms, pure python implementation, common interface, optional external libs usage.
Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models
A static analysis library for computing graph representations of Python programs suitable for use with graph neural networks.
A large collection of system log datasets for AI-driven log analytics [ISSRE'23]