Programming and execution model for parallel bounded exhaustive testing

Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)

The official Meta Llama 3 GitHub site

Object Graph Programming

A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 30.67% tasks (pass@1) in SWE-bench lite and 38.40% tasks (pass@1) in SWE-bench verified wi…

Automatic extraction of inline tests (from unit tests)

Analogweb Core Components

LDB: A Large Language Model Debugger via Verifying Runtime Execution Step by Step

Large Language Models for Software Engineering

Home of StarCoder2!

[ICLR 2024]: Is Self-Repair a Silver Bullet for Code Generation?

Bash function library

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supportin…

DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection and Instruction-Aware Models for Conversational AI

This repo includes ChatGPT prompt curation to use ChatGPT better.

Inference code for CodeLlama models

ML-based regression test selection

Tests that check correctness of a single statement

本人的科研经验

✨ RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems - ICLR 2024

A beautiful, simple, clean, and responsive Jekyll theme for academics

(Minimalism Style) Powered by Jekyll, based on the Minimal Mistakes theme and Jason Ansel's website

CodeTF: One-stop Transformer Library for State-of-the-art Code LLM

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

TeCo: an ML+Execution model for test completion

Instruct-tune LLaMA on consumer hardware

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.